INDEX

Explanations

food and cooking

np_max-act · gemini-2.0-flash

The neuron fires on food‐quality adjectives or qualifiers (e.g. “whole,” “full-fat,” “unsweetened”) in ingredient lists.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orted

-0.06

.Write

-0.06

tical

-0.06

.makedirs

-0.06

Card

-0.06

ovation

-0.06

romosome

-0.06

Salvar

-0.06

\Mail

-0.06

modation

-0.06

POSITIVE LOGITS

 county

0.07

ONES

0.06

_proto

0.06

 right

0.06

_VALID

0.06

ώς

0.06

 leaking

0.06

-г

0.06

 Declaration

0.06

){

0.06

Activations Density 0.011%

food and cooking

The neuron fires on food‐quality adjectives or qualifiers (e.g. “whole,” “full-fat,” “unsweetened”) in ingredient lists.

No Comments

No Known Activations