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
20-LLAMASCOPE-RES-32K
20716
Prev
Next
MODEL
20-llamascope-res-32k
Source/SAE
INDEX
Go
Explanations
phrases indicating certainty or assurance
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
LLAMA3.1-8B @ 20-llamascope-res-32k
Configuration
fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-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.20.hook_resid_post
Hook Layer
20
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/20-llamascope-res-32k/20716?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b/20-llamascope-res-32k/20716?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
vez
-0.16
-0.16
rey
-0.15
ega
-0.13
Pres
-0.13
P
-0.13
hle
-0.13
иÑĤÑĭ
-0.13
elda
-0.13
A
-0.13
POSITIVE LOGITS
ãĥ«ãĥĪ
0.17
ema
0.16
bÃŃ
0.15
utor
0.14
APON
0.14
ola
0.13
vx
0.13
ç¢
0.13
drs
0.13
cdr
0.13
Act
ivations
Density 0.172%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
