INDEX

Explanations

references to conspiracy theories and government covert operations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post

Features

65,536

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

gated

Context Size

1,024

Dataset

Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ofire

-0.14

ains

-0.14

elry

-0.14

 erupt

-0.14

 Inspection

-0.13

ifest

-0.13

ga

-0.13

Inspect

-0.12

 Sherlock

-0.12

ÃŃd

-0.12

POSITIVE LOGITS

 secret

0.41

 Secret

0.33

-secret

0.31

 SECRET

0.30

 secrets

0.30

 classified

0.29

secret

0.29

Secret

0.29

ç§ĺ

0.29

 secretly

0.28

Activations Density 0.051%

references to conspiracy theories and government covert operations

No Comments

No Known Activations