INDEX

Explanations

television

np_max-act · gemini-2.0-flash

This neuron activates on terms related to advertising or media campaigns (e.g., ads, TV, media, running, market).

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

_repo

-0.07

 Aure

-0.06

ذار

-0.06

 pleasure

-0.06

le

-0.06

 Manufact

-0.06

 Benton

-0.06

iks

-0.06

 Works

-0.06

 identify

-0.06

POSITIVE LOGITS

ismatic

0.07

 chạy

0.07

Slim

0.07

 réfé

0.07

*size

0.07

azines

0.06

-sem

0.06

 каб

0.06

 serm

0.06

нет

0.06

Activations Density 0.010%

television

This neuron activates on terms related to advertising or media campaigns (e.g., ads, TV, media, running, market).

No Comments

No Known Activations