INDEX

Explanations

and

np_max-act · gemini-2.0-flash

This neuron activates on numeric tokens—especially non‐integer or decimal number values.

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

 espect

-0.07

 marital

-0.07

xFF

-0.07

ристи

-0.07

 dips

-0.07

_preview

-0.06

fort

-0.06

 неправиль

-0.06

.reject

-0.06

_rom

-0.06

POSITIVE LOGITS

WebHost

0.06

 both

0.06

StartTime

0.06

the

0.06

 evento

0.06

‐

0.06

hold

0.06

COD

0.06

gun

0.06

Activations Density 0.036%

and

This neuron activates on numeric tokens—especially non‐integer or decimal number values.

No Comments

No Known Activations