INDEX

Explanations

components related to document formatting in programming or typesetting

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

 principals

-0.15

appen

-0.15

zych

-0.15

iteur

-0.15

ucht

-0.15

clearfix

-0.15

apy

-0.14

 Lights

-0.14

losion

-0.14

-tracking

-0.14

POSITIVE LOGITS

igue

0.16

ĵn

0.16

pler

0.15

plers

0.15

edia

0.15

lama

0.15

ãģŁãģĹ

0.15

à¸±à¸ĵà¸ĳ

0.15

furt

0.14

 Sphinx

0.14

Activations Density 0.008%

components related to document formatting in programming or typesetting

No Known Activations