© 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 · 71478 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
71478

INDEX

Explanations

Insurance policies

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

죄

-0.08

UCH

-0.07

्ट

-0.07

алог

-0.07

cat

-0.06

 motivating

-0.06

 Dram

-0.06

.left

-0.06

SA

-0.06

(proc

-0.06

POSITIVE LOGITS

_removed

0.06

 norske

0.06

_Query

0.06

unl

0.06

허

0.06

 additives

0.05

0.05

 clauses

0.05

>Status

0.05

 directions

0.05

Activations Density 0.015%

No Known Activations