INDEX

Explanations

General English text

np_max-act · gemini-2.0-flash

The neuron responds most strongly to verbs—especially words denoting actions or procedural steps.

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

 Johns

-0.07

 surrendered

-0.07

 northern

-0.06

pot

-0.06

 فر

-0.06

 الف

-0.06

 psychology

-0.06

Pt

-0.06

 obey

-0.06

 чому

-0.06

POSITIVE LOGITS

:,

0.07

รณ

0.06

fj

0.06

_gs

0.06

among

0.06

ScrollPane

0.06

 strand

0.06

abetic

0.06

(Expected

0.06

Activations Density 0.503%

General English text

The neuron responds most strongly to verbs—especially words denoting actions or procedural steps.

No Comments

No Known Activations