Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
31-LLAMASCOPE-RES-131K
11502
Prev
Next
MODEL
31-llamascope-res-131k
Source/SAE
INDEX
Go
Explanations
patterns involving specific characters or symbols within data structures
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/llama3.1-8b/31-llamascope-res-131k/11502?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b/31-llamascope-res-131k/11502?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
,
-0.07
ephy
-0.06
↵
-0.05
-0.05
,B
-0.05
@Id
-0.05
avn
-0.05
BT
-0.05
zin
-0.05
_nc
-0.05
POSITIVE LOGITS
w
0.13
r
0.10
ï½¢
0.10
i
0.10
("#{
0.09
q
0.09
W
0.09
Q
0.08
/#{
0.08
{↵
0.07
Act
ivations
Density 0.004%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
