© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 94039 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
94039

INDEX

Explanations

told

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

 embry

-0.07

McA

-0.07

 impulse

-0.07

.."

-0.06

 Schmidt

-0.06

 landmarks

-0.06

operators

-0.06

Containing

-0.06

 Şimdi

-0.06

 довольно

-0.06

POSITIVE LOGITS

pais

0.06

тиров

0.06

(cljs

0.06

보다

0.06

朱

0.06

.choices

0.06

bao

0.06

Você

0.06

_obs

0.05

 ellos

0.05

Activations Density 0.231%

No Known Activations