INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron activates on tokens that are multiword identifiers containing underscores (e.g. snake_case or underscore-separated names).

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

Sab

-0.06

vinc

-0.06

 identifiable

-0.06

expenses

-0.06

 bloodstream

-0.06

/screens

-0.06

dí

-0.06

िछ

-0.06

 Keyword

-0.06

ERR

-0.05

POSITIVE LOGITS

Toolkit

0.07

�

0.07

.runner

0.07

 Plug

0.07

 climb

0.07

.context

0.06

coverage

0.06

 catch

0.06

_ub

0.06

ToFile

0.06

Activations Density 0.057%

code

This neuron activates on tokens that are multiword identifiers containing underscores (e.g. snake_case or underscore-separated names).

No Comments

No Known Activations