© 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 · 19-RESID-POST-AA · 29892 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
19-RESID-POST-AA
29892

INDEX

Explanations

damage

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_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

áč

-0.06

ENER

-0.06

 >
↵

-0.06

leniyor

-0.06

álně

-0.06

úb

-0.06

 mogelijk

-0.06

 reluctant

-0.06

ारन

-0.06

toLocale

-0.06

POSITIVE LOGITS

gab

0.07

 elites

0.07

.leave

0.07

((&

0.07

 επί

0.07

 Impact

0.06

='\

0.06

 causal

0.06

.shutdown

0.06

 Clinical

0.06

Activations Density 0.017%

No Known Activations