INDEX

Explanations

references to code features or methods

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ÑĢÑĥÐ¿Ð¿

-0.16

isposable

-0.15

'%$

-0.14

endoza

-0.14

æ£

-0.14

icare

-0.14

endant

-0.14

erd

-0.14

thic

-0.14

à¸£à¸ĵ

-0.14

POSITIVE LOGITS

gov

0.15

 FALL

0.15

egin

0.14

 Synd

0.14

 spontaneous

0.13

Hed

0.13

omen

0.13

utor

0.13

reg

0.13

Ð¾Ð»Ð¶

0.13

Activations Density 0.160%

references to code features or methods

No Known Activations