INDEX

Explanations

unstructured text/code snippets

np_max-act · gemini-2.0-flash

The neuron responds to content words—especially verbs—marking action words rather than function words.

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

 specializes

-0.06

resultCode

-0.06

College

-0.06

 showToast

-0.06

JSGlobal

-0.06

 μετα

-0.06

ół

-0.06

"=>$

-0.06

pués

-0.06

@store

-0.06

POSITIVE LOGITS

=P

0.07

=str

0.06

ouses

0.06

SCALL

0.06

 Pharmac

0.06

series

0.06

میل

0.06

 sunset

0.06

 bartender

0.06

 Jewelry

0.06

Activations Density 0.200%

unstructured text/code snippets

The neuron responds to content words—especially verbs—marking action words rather than function words.

No Comments

No Known Activations