INDEX

Explanations

phrases related to indicators or symptoms of change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

exels

-0.17

acin

-0.16

stood

-0.15

ATED

-0.15

ewan

-0.14

avaÅŁ

-0.14

_SCENE

-0.14

riot

-0.14

/mail

-0.13

erli

-0.13

POSITIVE LOGITS

 pointing

0.23

posting

0.21

posts

0.19

posted

0.19

pointer

0.19

 indicating

0.19

 indic

0.19

istr

0.18

alerts

0.17

 indicate

0.16

Activations Density 0.022%

phrases related to indicators or symptoms of change

No Comments

No Known Activations