INDEX

Explanations

phrases that express uncertainty or speculation about knowledge and beliefs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áº§n

-0.16

iley

-0.15

áº¿u

-0.15

ĨĴ

-0.14

anship

-0.14

ofil

-0.14

umpt

-0.13

iphers

-0.13

soever

-0.13

POSITIVE LOGITS

 what

0.24

what

0.19

how

0.19

 maybe

0.18

maybe

0.17

 where

0.15

 until

0.15

 Maybe

0.15

ä»Ģä¹Ī

0.15

 future

0.14

Activations Density 0.020%

phrases that express uncertainty or speculation about knowledge and beliefs

No Comments

No Known Activations