INDEX

Explanations

general

np_max-act · gemini-2.0-flash

The neuron specializes in spotting mentions of elections and their results (e.g. “primary,” “general election,” vote tallies, winners/defeated”).

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

 folded

-0.08

 оці

-0.07

dde

-0.06

 абсолют

-0.06

 Economics

-0.06

 retrieve

-0.06

 tomb

-0.06

 Licht

-0.06

美國

-0.06

Utc

-0.06

POSITIVE LOGITS

.ERR

0.07

 ра

0.07

plays

0.07

 perpetrated

0.06

 asıl

0.06

Tomorrow

0.06

Members

0.06

 dần

0.06

nop

0.06

 decisive

0.06

Activations Density 0.002%

general

The neuron specializes in spotting mentions of elections and their results (e.g. “primary,” “general election,” vote tallies, winners/defeated”).

No Comments

No Known Activations