INDEX

Explanations

game show

np_max-act · gemini-2.0-flash

This neuron detects mentions of a televised quiz or game‐show context (e.g., the words “game show,” “Jeopardy,” and related terms).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}),↵

-0.07

 estados

-0.07

:k

-0.07

Crear

-0.07

igram

-0.07

_ll

-0.06

 Predicate

-0.06

 Tests

-0.06

 přeh

-0.06

POSITIVE LOGITS

':'

0.07

__(*

0.06

ATHER

0.06

_tra

0.06

Optimizer

0.06

.Do

0.05

stice

0.05

_peak

0.05

.React

0.05

([[

0.05

Activations Density 0.006%

game show

This neuron detects mentions of a televised quiz or game‐show context (e.g., the words “game show,” “Jeopardy,” and related terms).

No Comments

No Known Activations