Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
15-RESID-POST-AA
108718
Prev
Next
MODEL
15-resid-post-aa
Source/SAE
INDEX
Go
Explanations
period
np_max-act · gemini-2.0-flash
No Scores
The neuron activates on words at the beginnings of sentences or section/paragraph starts (sentence-initial, often capitalized tokens).
oai_token-act-pair · gpt-5-mini
Triggered by @vetterc0
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
How To Load
Dataset (Dashboard)
Various
Features
131,072
Data Type
float32
Hook Name
blocks.15.hook_resid_post
Architecture
standard
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/llama3.1-8b-it/15-resid-post-aa/108718?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b-it/15-resid-post-aa/108718?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
(visitor
-0.07
,self
-0.07
-mile
-0.07
/state
-0.07
再
-0.07
zoom
-0.06
而
-0.06
th
-0.06
Notice
-0.06
_known
-0.06
POSITIVE LOGITS
.
0.10
).
0.10
).
0.10
?
0.10
”.
0.09
%).
0.09
”).
0.09
ी.
0.08
}.
0.08
े.
0.08
Act
ivations
Density 2.185%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
