© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

LLAMA3.1-8B-IT · 11-RESID-POST-AA · 100079 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
100079

INDEX

Explanations

equations

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

üml

-0.07

fname

-0.07

 Lehr

-0.07

 kosher

-0.06

/apache

-0.06

 Müdür

-0.06

 Conserv

-0.06

.abspath

-0.05

 función

-0.05

чного

-0.05

POSITIVE LOGITS

stk

0.08

Codec

0.07

 ilişk

0.07

ZX

0.07

_pulse

0.06

0.06

 recognition

0.06

-uri

0.06

0.06

ABD

0.06

Activations Density 0.004%

No Known Activations