INDEX

Explanations

Coal

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the string “Coal” (typically as the standalone word or prefix at the start of tokens).

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

borg

-0.08

 Hend

-0.06

.getD

-0.06

 photos

-0.06

enden

-0.06

(resp

-0.06

 electronic

-0.06

 Flask

-0.06

šší

-0.06

plevel

-0.06

POSITIVE LOGITS

 Coal

0.16

 coal

0.16

Coal

0.13

coal

0.09

 charcoal

0.08

 Coalition

0.07

++)

0.07

 좋아

0.07

 dříve

0.07

.Priority

0.06

Activations Density 0.004%

Coal

This neuron detects occurrences of the string “Coal” (typically as the standalone word or prefix at the start of tokens).

No Comments

No Known Activations

Coal

This neuron detects occurrences of the string “Coal” (typically as the standalone word or prefix at the start of tokens).

No Comments

No Known Activations