INDEX

Explanations

were

np_max-act · gemini-2.0-flash

The neuron fires for semantically “content‐bearing” words (nouns, adjectives, and other key content words), not for function words or punctuation.

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

ricia

-0.07

또

-0.07

 landsc

-0.07

узы

-0.06

keepers

-0.06

osta

-0.06

ічних

-0.06

remely

-0.06

inely

-0.06

 difícil

-0.06

POSITIVE LOGITS

_wifi

0.07

.Exists

0.06

(MigrationBuilder

0.06

ehr

0.06

.dim

0.06

 subrange

0.06

 프로

0.06

@Bean

0.06

 Reporter

0.06

 Satan

0.06

Activations Density 0.061%

were

The neuron fires for semantically “content‐bearing” words (nouns, adjectives, and other key content words), not for function words or punctuation.

No Comments

No Known Activations