Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Blog
Slack
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
Residual Stream
25-LLAMASCOPE-RES-32K
13900
Prev
Next
MODEL
25-llamascope-res-32k
Source/SAE
INDEX
Go
Explanations
words or characters from non-Latin alphabets or special encoding characters
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 @ 25-llamascope-res-32k
Configuration
fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-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.25.hook_resid_post
Hook Layer
25
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/25-llamascope-res-32k/13900?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b/25-llamascope-res-32k/13900?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
efeller
-0.18
alace
-0.15
æµ´
-0.15
aic
-0.15
ifikasi
-0.15
cts
-0.14
ifar
-0.14
inth
-0.14
ابÛĮ
-0.14
Ð®ÐĽ
-0.14
POSITIVE LOGITS
t
0.24
n
0.23
l
0.21
r
0.20
m
0.19
d
0.19
ule
0.15
g
0.15
s
0.15
eki
0.15
Act
ivations
Density 0.033%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
