INDEX

Explanations

racing

np_max-act · gemini-2.0-flash

The neuron fires on descriptive performance commentary—phrases evaluating how well something (often a race car) handles or suits particular conditions.

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

 tâm

-0.08

Gem

-0.07

為

-0.07

ducers

-0.06

 jíd

-0.06

 constituents

-0.06

ducer

-0.06

 feelings

-0.06

nou

-0.06

 }};↵

-0.06

POSITIVE LOGITS

 Regardless

0.07

 Recomm

0.07

 subtract

0.07

Whitespace

0.06

 Successful

0.06

Regardless

0.06

-await

0.06

ไร

0.06

 oblivious

0.06

 relying

0.06

Activations Density 0.090%

racing

The neuron fires on descriptive performance commentary—phrases evaluating how well something (often a race car) handles or suits particular conditions.

No Comments

No Known Activations

racing

The neuron fires on descriptive performance commentary—phrases evaluating how well something (often a race car) handles or suits particular conditions.

No Comments

No Known Activations