Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Realmbird
Karma:
74
All
Posts
Comments
New
Top
Old
NLA Thought Anchors
Realmbird
31 May 2026 23:38 UTC
10
points
3
comments
4
min read
LW
link
NLA Verbalizations on AuditBench: Llama 70B
Realmbird
16 May 2026 5:25 UTC
10
points
0
comments
3
min read
LW
link
MHC Interp #1: Previous-Token Heads Become Attention Sinks Under Manifold-Constrained Hyper-Connections
Realmbird
3 May 2026 11:06 UTC
21
points
2
comments
5
min read
LW
link
Latent Reasoning Sprint #4: PCA Analysis on CoDI
Realmbird
18 Apr 2026 21:25 UTC
7
points
0
comments
3
min read
LW
link
Latent Reasoning Sprint #3: Activation Difference Steering and Logit Lens
Realmbird
4 Apr 2026 3:56 UTC
15
points
0
comments
4
min read
LW
link
Latent Reasoning Sprint #2: Token-Based Signals and Linear Probes
Realmbird
19 Mar 2026 3:39 UTC
6
points
0
comments
3
min read
LW
link
Latent Reasoning Sprint #1: Tuned Lens and Logit Lens on CODI
Realmbird
6 Mar 2026 18:36 UTC
7
points
1
comment
4
min read
LW
link
Exploration of Counterfactual Importance and Attention Heads
Realmbird
30 Sep 2025 1:17 UTC
13
points
0
comments
6
min read
LW
link
Back to top