INDEX

Explanations

offering help

np_max-act · gemini-2.0-flash

This neuron appears to be inactive (i.e. “dead”)—it does not respond to any input 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_TEM

-0.06

uj

-0.06

uu

-0.06

Dt

-0.06

SSC

-0.06

 candidate

-0.06

\Abstract

-0.06

UrlParser

-0.06

->_

-0.06

")));↵↵

-0.06

POSITIVE LOGITS

ализа

0.07

 bước

0.06

 typeName

0.06

_ty

0.06

_Syntax

0.06

SEMB

0.06

@Service

0.06

 верес

0.06

 dazzling

0.06

uania

0.06

Activations Density 0.011%

offering help

This neuron appears to be inactive (i.e. “dead”)—it does not respond to any input tokens.

No Comments

No Known Activations