© 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 · 15-RESID-POST-AA · 68345 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
15-RESID-POST-AA
68345

INDEX

Explanations

himself

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

Starting

-0.08

.debugLine

-0.07

нє

-0.07

收

-0.06

 defaultProps

-0.06

COS

-0.06

こんに

-0.06

}"↵↵

-0.06

pag

-0.06

 růz

-0.06

POSITIVE LOGITS

0.07

افظ

0.07

 Seed

0.07

 enumerator

0.07

 seed

0.06

_empty

0.06

.gravity

0.06

	Config

0.06

_terms

0.06

//_

0.06

Activations Density 0.099%

No Known Activations