INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

This neuron activates on floating-point numeric scores or decimal 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

atham

-0.06

atto

-0.06

 Lift

-0.06

 tidal

-0.06

 Nokia

-0.06

 Dive

-0.06

 ulcer

-0.06

holm

-0.06

Fuk

-0.06

 Sierra

-0.06

POSITIVE LOGITS

_proba

0.07

उत

0.07

 Outlet

0.07

هـ

0.07

 Kıs

0.06

_mot

0.06

 فيلم

0.06

 configure

0.06

(PRO

0.06

일본

0.06

Activations Density 0.008%

punctuation

This neuron activates on floating-point numeric scores or decimal numbers in the text.

No Comments

No Known Activations

punctuation

This neuron activates on floating-point numeric scores or decimal numbers in the text.

No Comments

No Known Activations