© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
LLAMA3.1-8B · 22-LLAMASCOPE-RES-131K · 4205 ｜ Neuronpedia
Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
22-LLAMASCOPE-RES-131K
4205
Prev
Next
MODEL
22-llamascope-res-131k
Source/SAE
INDEX
Go
Explanations
non-textual characters or symbols used in formatting or markup
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
cerebras/SlimPajama-627B
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/llama3.1-8b/22-llamascope-res-131k/4205?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b/22-llamascope-res-131k/4205?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
loser
-0.07
íĥĦ
-0.07
Kane
-0.07
Å¥
-0.07
otta
-0.07
ps
-0.07
íĥľ
-0.07
зÑĭ
-0.07
tring
-0.06
aran
-0.06
POSITIVE LOGITS
×ķ×
0.12
×Ļ×
0.10
×
0.09
×Ķ
0.09
×ij
0.09
×ŀ
0.09
×Ķ
0.08
ת
0.08
×
0.08
×ķ
0.08
Act
ivations
Density 0.017%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
