© 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 · 11-RESID-POST-AA · 17576 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT
Resid Post - 131k
11-RESID-POST-AA
17576

INDEX

Explanations

.

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

ae

-0.07

-0.06

-dependent

-0.06

 Trash

-0.06

,n

-0.06

	temp

-0.06

Hou

-0.06

４

-0.06

,is

-0.06

stalk

-0.06

POSITIVE LOGITS

]])↵↵

0.07

 ذه

0.07

TabIndex

0.07

.”↵↵↵↵

0.07

 paused

0.06

fails

0.06

_truth

0.06

[method

0.06

_units

0.06

------↵

0.06

Activations Density 0.001%

No Known Activations