© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 7-RESID-POST-AA · 119698 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
119698

INDEX

Explanations

attachment

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

atics

-0.08

 جامعه

-0.06

Ni

-0.06

Executable

-0.06

 đem

-0.06

 wasm

-0.06

 готов

-0.06

.gson

-0.06

.getToken

-0.06

 تك

-0.06

POSITIVE LOGITS

::↵↵

0.07

 affirm

0.07

_DAY

0.07

 Falling

0.07

程

0.06

-hook

0.06

_TypeDef

0.06

undan

0.06

 kilometres

0.06

_definitions

0.06

Activations Density 0.032%

No Known Activations