INDEX

Explanations

books and texts

np_max-act · gemini-2.0-flash

This neuron activates on mentions of written works or textual titles, i.e. references to specific books or texts.

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

톡

-0.06

xEE

-0.06

-map

-0.06

DI

-0.06

[state

-0.06

ımlı

-0.06

-football

-0.06

 influence

-0.06

kHz

-0.06

Message

-0.06

POSITIVE LOGITS

ivel

0.07

언

0.07

 Karn

0.07

 EntityManager

0.06

igrant

0.06

 Harness

0.06

 extra

0.06

extra

0.06

 narrowing

0.06

Activations Density 0.037%

books and texts

This neuron activates on mentions of written works or textual titles, i.e. references to specific books or texts.

No Comments

No Known Activations

books and texts

This neuron activates on mentions of written works or textual titles, i.e. references to specific books or texts.

No Comments

No Known Activations