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
29-LLAMASCOPE-RES-32K
3125
Prev
Next
MODEL
29-llamascope-res-32k
Source/SAE
INDEX
Go
Explanations
technical terms and structured phrases related to programming and database management
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
Comparing With
LLAMA3.1-8B @ 29-llamascope-res-32k
Configuration
fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
cerebras/SlimPajama-627B
Features
32,768
Data Type
bfloat16
Hook Name
blocks.29.hook_resid_post
Hook Layer
29
Architecture
jumprelu
Context Size
1,024
Dataset
cerebras/SlimPajama-627B
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/llama3.1-8b/29-llamascope-res-32k/3125?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b/29-llamascope-res-32k/3125?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
urf
-0.19
bar
-0.19
obar
-0.19
bar
-0.19
Bart
-0.19
strup
-0.18
Bar
-0.17
(bar
-0.16
-Bar
-0.16
-bar
-0.16
POSITIVE LOGITS
Pat
0.35
pat
0.33
PAT
0.33
pat
0.32
Pat
0.32
PAT
0.31
паÑĤ
0.27
_pat
0.24
(pat
0.24
Patt
0.23
Act
ivations
Density 0.033%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
