INDEX

Explanations

human

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of the word “human.”

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

 addon

-0.07

voj

-0.07

Aly

-0.07

Newsletter

-0.06

 suff

-0.06

elt

-0.06

 fees

-0.06

 wealthy

-0.06

 Welch

-0.06

Lu

-0.06

POSITIVE LOGITS

oppable

0.07

 supply

0.07

_equiv

0.06

imest

0.06

adaptiveStyles

0.06

 речов

0.06

VERRIDE

0.06

 influ

0.06

ClientId

0.06

ลาด

0.06

Activations Density 0.016%

human

The neuron fires on occurrences of the word “human.”

No Comments

No Known Activations