INDEX

Explanations

reviews

np_max-act · gemini-2.0-flash

The neuron fires on numeric review scores and rating‐related metadata (e.g. “score,” “rating,” “reviews,” and their accompanying numbers”).

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

.detach

-0.07

.waitKey

-0.06

 dinner

-0.06

 chắc

-0.06

尾

-0.06

 créd

-0.06

 удоб

-0.06

.word

-0.06

 معرفی

-0.06

网

-0.06

POSITIVE LOGITS

lotte

0.07

wiki

0.07

_fit

0.07

Creates

0.06

 utilise

0.06

']):

0.06

Inactive

0.06

orsche

0.06

ledo

0.06

Activations Density 0.002%

reviews

The neuron fires on numeric review scores and rating‐related metadata (e.g. “score,” “rating,” “reviews,” and their accompanying numbers”).

No Comments

No Known Activations