INDEX

Explanations

speech

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the phrase “hate speech.”

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

.Price

-0.06

 سكان

-0.06

ेण

-0.06

 Destiny

-0.06

 ling

-0.06

 Arbitrary

-0.06

 Аз

-0.06

 liberty

-0.06

 KING

-0.06

POSITIVE LOGITS

۲۰۲

0.07

 slur

0.07

 whereabouts

0.06

(exc

0.06

 anzeigen

0.06

 jitter

0.06

TypeInfo

0.06

jsx

0.06

 consistently

0.06

 tightening

0.06

Activations Density 0.003%

speech

The neuron fires on occurrences of the phrase “hate speech.”

No Comments

No Known Activations

speech

The neuron fires on occurrences of the phrase “hate speech.”

No Comments

No Known Activations