INDEX

Explanations

actions related to showing, looking, and creating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÂŃing

-0.24

ings

-0.21

Ã©gor

-0.18

ingen

-0.18

Ã¡o

-0.17

osterone

-0.16

song

-0.16

Ńå·ŀ

-0.16

/remove

-0.16

sv

-0.16

POSITIVE LOGITS

gg

0.18

REDIENT

0.18

ame

0.17

redient

0.17

redients

0.17

hausen

0.17

tor

0.16

ton

0.16

ditor

0.16

irc

0.16

Activations Density 0.160%

actions related to showing, looking, and creating

No Comments

No Known Activations