© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 24964 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
24964

INDEX

Explanations

biological weapons

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

布

-0.07

 شهرد

-0.06

CVE

-0.06

 Jews

-0.06

任

-0.06

.Roll

-0.06

-0.06

ukkit

-0.06

イル

-0.06

 pagan

-0.06

POSITIVE LOGITS

 glitches

0.07

.Is

0.07

 traf

0.07

_Bool

0.07

VarChar

0.06

-email

0.06

 envelopes

0.06

 Serialized

0.06

masters

0.06

anno

0.06

Activations Density 0.010%

No Known Activations