INDEX

Explanations

-

np_max-act · gemini-2.0-flash

This neuron detects the dash or hyphen tokens that introduce author-list entries.

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

้ช

-0.07

령

-0.07

 attic

-0.07

 بو

-0.06

FullPath

-0.06

 Terms

-0.06

 ocur

-0.06

 wards

-0.06

ть

-0.06

 terms

-0.06

POSITIVE LOGITS

 Swal

0.06

 Centro

0.06

 road

0.06

 singular

0.06

_barrier

0.06

:ss

0.06

zan

0.06

 prudent

0.06

boro

0.06

pg

0.06

Activations Density 0.001%

-

This neuron detects the dash or hyphen tokens that introduce author-list entries.

No Comments

No Known Activations