INDEX

Explanations

instrumental

np_max-act · gemini-2.0-flash

The neuron fires on descriptive words that signal someone’s important or prominent role or contribution (e.g. “instrumental,” “prominent,” “figure,” “played a key role,” etc.).

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

-0.06

shadow

-0.06

etermined

-0.06

 reader

-0.06

 utils

-0.06

:none

-0.06

_params

-0.06

-arm

-0.06

 successor

-0.06

 enclosure

-0.06

POSITIVE LOGITS

ิ่

0.07

ائز

0.07

άς

0.07

الية

0.07

 fontStyle

0.06

 tưởng

0.06

aryawan

0.06

اسة

0.06

€↵

0.06

 Evropské

0.06

Activations Density 0.024%

instrumental

The neuron fires on descriptive words that signal someone’s important or prominent role or contribution (e.g. “instrumental,” “prominent,” “figure,” “played a key role,” etc.).

No Comments

No Known Activations