INDEX

Explanations

code

np_max-act · gemini-2.0-flash

This neuron remains inactive and does not respond to any tokens.

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

front

-0.07

 loro

-0.07

 Aggregate

-0.06

products

-0.06

 nedenle

-0.06

 current

-0.06

_flip

-0.06

ислов

-0.06

 Shea

-0.06

POSITIVE LOGITS

elm

0.07

Ast

0.06

owment

0.06

徒歩

0.06

 PdfP

0.06

(){

0.06

QUIRE

0.06

ORLD

0.06

(provider

0.06

г

0.06

Activations Density 0.032%

code

This neuron remains inactive and does not respond to any tokens.

No Comments

No Known Activations