RSS

Senthooran Rajamanoharan

Karma: 1,859

How well do mod­els fol­low their con­sti­tu­tions?

12 Mar 2026 0:07 UTC
87 points
4 comments26 min readLW link

Cur­rent ac­ti­va­tion or­a­cles are hard to use

3 Mar 2026 19:33 UTC
77 points
3 comments16 min readLW link

How to De­sign En­vi­ron­ments for Un­der­stand­ing Model Motives

2 Mar 2026 7:14 UTC
39 points
0 comments10 min readLW link

Why Did My Model Do That? Model In­crim­i­na­tion for Di­ag­nos­ing LLM Misbehavior

27 Feb 2026 3:20 UTC
49 points
1 comment78 min readLW link

mod­els have some pretty funny at­trac­tor states

12 Feb 2026 21:14 UTC
266 points
38 comments18 min readLW link

Test your in­ter­pretabil­ity tech­niques by de-cen­sor­ing Chi­nese models

15 Jan 2026 16:33 UTC
90 points
14 comments20 min readLW link

Brief Ex­plo­ra­tions in LLM Value Rankings

12 Jan 2026 18:16 UTC
37 points
1 comment11 min readLW link

Prin­ci­pled In­ter­pretabil­ity of Re­ward Hack­ing in Closed Fron­tier Models

1 Jan 2026 16:37 UTC
24 points
0 comments23 min readLW link

An­nounc­ing Gemma Scope 2

22 Dec 2025 21:56 UTC
95 points
1 comment2 min readLW link

Can we in­ter­pret la­tent rea­son­ing us­ing cur­rent mechanis­tic in­ter­pretabil­ity tools?

22 Dec 2025 16:56 UTC
37 points
0 comments9 min readLW link

How Can In­ter­pretabil­ity Re­searchers Help AGI Go Well?

1 Dec 2025 13:05 UTC
66 points
1 comment14 min readLW link

A Prag­matic Vi­sion for Interpretability

1 Dec 2025 13:05 UTC
131 points
39 comments27 min readLW link

Cur­rent LLMs seem to rarely de­tect CoT tampering

19 Nov 2025 15:27 UTC
55 points
0 comments20 min readLW link

Steer­ing Out-of-Distri­bu­tion Gen­er­al­iza­tion with Con­cept Abla­tion Fine-Tuning

23 Jul 2025 14:57 UTC
79 points
8 comments5 min readLW link

Nar­row Misal­ign­ment is Hard, Emer­gent Misal­ign­ment is Easy

14 Jul 2025 21:05 UTC
134 points
24 comments5 min readLW link

Self-preser­va­tion or In­struc­tion Am­bi­guity? Ex­am­in­ing the Causes of Shut­down Resistance

14 Jul 2025 14:52 UTC
86 points
19 comments11 min readLW link

Con­ver­gent Lin­ear Rep­re­sen­ta­tions of Emer­gent Misalignment

16 Jun 2025 15:47 UTC
76 points
1 comment8 min readLW link

Model Or­ganisms for Emer­gent Misalignment

16 Jun 2025 15:46 UTC
118 points
19 comments5 min readLW link

In­terim Re­search Re­port: Mechanisms of Awareness

2 May 2025 20:29 UTC
43 points
6 comments8 min readLW link

Nega­tive Re­sults for SAEs On Down­stream Tasks and Depri­ori­tis­ing SAE Re­search (GDM Mech In­terp Team Progress Up­date #2)

26 Mar 2025 19:07 UTC
116 points
15 comments29 min readLW link
(deepmindsafetyresearch.medium.com)