INDEX

Explanations

.

np_max-act · gemini-2.0-flash

The neuron is detecting numeric literal tokens (especially floating‐point numbers) in the text.

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

 IMapper

-0.07

 confronting

-0.06

KEN

-0.06

CMS

-0.06

%</

-0.06

 hearings

-0.06

tell

-0.06

:/

-0.06

iest

-0.06

 meetings

-0.06

POSITIVE LOGITS

ファ

0.07

.m

0.06

 Forecast

0.06

امه

0.06

エ

0.06

 आग

0.06

CTX

0.06

 dopamine

0.06

oma

0.06

&_

0.06

Activations Density 0.001%

.

The neuron is detecting numeric literal tokens (especially floating‐point numbers) in the text.

No Comments

No Known Activations

.

The neuron is detecting numeric literal tokens (especially floating‐point numbers) in the text.

No Comments

No Known Activations