INDEX

Explanations

distance

np_max-act · gemini-2.0-flash

This neuron never fires (all activations are zero), so it doesn’t detect any pattern—it’s effectively “dead.”

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

mc

-0.07

 Israelis

-0.07

-menu

-0.07

Hillary

-0.07

кс

-0.07

Productos

-0.06

İn

-0.06

participant

-0.06

etration

-0.06

POSITIVE LOGITS

�

0.07

 apprec

0.07

ta

0.06

 avail

0.06

ณะ

0.06

blah

0.06

getJSON

0.06

_DURATION

0.06

 prolong

0.06

 rendered

0.06

Activations Density 0.014%

distance

This neuron never fires (all activations are zero), so it doesn’t detect any pattern—it’s effectively “dead.”

No Comments

No Known Activations