© 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 · 93818 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
7-RESID-POST-AA
93818

INDEX

Explanations

election

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

ап

-0.07

aps

-0.06

 lookup

-0.06

ーロ

-0.06

neği

-0.06

Ş

-0.06

�

-0.06

 Begin

-0.06

esh

-0.06

urred

-0.06

POSITIVE LOGITS

 Cartesian

0.06

	record

0.06

_NUMERIC

0.06

_favorite

0.06

IOS

0.06

.FromSeconds

0.06

 opioids

0.06

.textLabel

0.06

xlim

0.05

.RemoveAt

0.05

Activations Density 0.018%

No Known Activations