© 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 · 40048 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
40048

INDEX

Explanations

lengthy text

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

 Psychological

-0.06

_callback

-0.06

nah

-0.06

-rights

-0.06

qing

-0.06

_TEX

-0.06

管

-0.06

 thẩm

-0.06

享

-0.06

 Stuart

-0.06

POSITIVE LOGITS

!
↵

0.07

 mascul

0.07

;">↵

0.06

 NASA

0.06

洛

0.06

 disagrees

0.06

:*

0.06

require

0.06

벤

0.06

杜

0.06

Activations Density 0.201%

No Known Activations