INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron fires on numeric literal tokens (especially floating-point constants) in code.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

literal

-0.07

 بإ

-0.06

 contraction

-0.06

影響

-0.06

	client

-0.06

 SOFTWARE

-0.06

 flavour

-0.06

 breastfeeding

-0.06

SUN

-0.06

ERRUPT

-0.06

POSITIVE LOGITS

Jag

0.08

_CODES

0.06

_ARG

0.06

 salary

0.06

_FRAME

0.06

_Selected

0.06

,val

0.06

marshal

0.06

を行

0.06

acia

0.06

Activations Density 0.023%

code

The neuron fires on numeric literal tokens (especially floating-point constants) in code.

No Comments

No Known Activations