INDEX

Explanations

Random data generation

np_max-act · gemini-2.0-flash

This neuron activates on document markup and code‐formatting tokens (e.g. backslashes, braces, percent signs, and other programming or LaTeX command symbols).

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

 shooter

-0.06

 kanıt

-0.06

rnd

-0.06

context

-0.06

ladık

-0.06

fra

-0.05

績

-0.05

',['

-0.05

ForeignKey

-0.05

lvl

-0.05

POSITIVE LOGITS

cen

0.07

 talked

0.07

 зак

0.07

-grey

0.07

 Persons

0.07

="'.

0.07

(\'

0.06

 orbit

0.06

 document

0.06

عب

0.06

Activations Density 0.007%

Random data generation

This neuron activates on document markup and code‐formatting tokens (e.g. backslashes, braces, percent signs, and other programming or LaTeX command symbols).

No Comments

No Known Activations