INDEX

Explanations

for

np_max-act · gemini-2.0-flash

This neuron responds to the word “for” when it appears as part of an explicit instruction phrase (e.g. “set for”).

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

YSIS

-0.07

CustomerId

-0.07

.Messages

-0.07

_POS

-0.06

addListener

-0.06

ortion

-0.06

drawable

-0.06

 entert

-0.06

urt

-0.06

(cin

-0.06

POSITIVE LOGITS

 kişisel

0.07

REV

0.07

sh

0.06

 Playlist

0.06

 Aberdeen

0.06

 Para

0.06

levelname

0.06

 Andr

0.06

 мали

0.06

Cou

0.06

Activations Density 0.001%

for

This neuron responds to the word “for” when it appears as part of an explicit instruction phrase (e.g. “set for”).

No Comments

No Known Activations