INDEX

Explanations

This neuron responds to the main content word at the start of list items or bullet‐style 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

getIndex

-0.07

Study

-0.07

Vy

-0.07

iente

-0.06

likle

-0.06

.Solid

-0.06

NIEnv

-0.06

 double

-0.06

POSITIVE LOGITS

 đặc

0.06

 pudding

0.06

quo

0.06

'http

0.06

dream

0.06

categories

0.06

usher

0.06

 krás

0.06

_ai

0.06

fun

0.06

Activations Density 0.075%

This neuron responds to the main content word at the start of list items or bullet‐style entries.

No Comments

No Known Activations