INDEX

Explanations

news media

np_max-act · gemini-2.0-flash

The neuron detects mentions of broadcast news outlets, programs, and on‐air personalities (e.g., network names like NBC/CBS/ABC, show titles, and anchors).

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

уд

-0.07

λοι

-0.06

TVs

-0.06

 Fathers

-0.06

鳥

-0.06

CAP

-0.06

 domest

-0.06

 LORD

-0.06

界

-0.06

POSITIVE LOGITS

%%%%%%%%%%%%%%%%

0.07

 getConnection

0.06

 açıklam

0.06

 Astroph

0.06

={"/

0.06

(tmp

0.06

.\

0.06

 сб

0.06

\",\

0.06

Doctrine

0.06

Activations Density 0.015%

news media

The neuron detects mentions of broadcast news outlets, programs, and on‐air personalities (e.g., network names like NBC/CBS/ABC, show titles, and anchors).

No Comments

No Known Activations