© 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 · 23-RESID-POST-AA · 101412 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
23-RESID-POST-AA
101412

INDEX

Explanations

in

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

 AssertionError

-0.07

Nov

-0.07

Я

-0.06

 Bernardino

-0.06

Nov

-0.06

ač

-0.06

 anticipate

-0.06

pras

-0.06

-0.06

契

-0.06

POSITIVE LOGITS

],"

0.07

YTE

0.07

.metric

0.06

 tuning

0.06

(newState

0.06

(Graphics

0.06

.caption

0.06

ักท

0.06

(hdc

0.06

*)"

0.06

Activations Density 0.070%

No Known Activations