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
43850
Prev
Next
MODEL
31-llamascope-res-131k
Source/SAE
INDEX
Go
Explanations
mathematical expressions or equations involving variables and operations
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/43850?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/43850?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
in
-0.11
the
-0.10
is
-0.10
as
-0.10
a
-0.10
for
-0.09
an
-0.09
on
-0.09
at
-0.09
to
-0.09
POSITIVE LOGITS
*\
0.11
\
0.11
0
0.10
*$
0.10
`\
0.10
-\
0.10
'\
0.10
âĻ¡
0.10
\$
0.10
yans
0.10
Act
ivations
Density 0.227%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
