INDEX

Explanations

references to business-related concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Mare

-0.15

Ø®Øµ

-0.15

mare

-0.14

atology

-0.14

gro

-0.14

åĩĿ

-0.14

alt

-0.14

è¼Ŀ

-0.14

POSITIVE LOGITS

combe

0.18

igu

0.16

wie

0.15

rans

0.15

/art

0.14

ouri

0.14

orno

0.14

orns

0.14

tram

0.14

inals

0.14

Activations Density 0.037%

references to business-related concepts and terms

No Comments

No Known Activations