INDEX

Explanations

references to human experience and medical implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iales

-0.20

kees

-0.15

DeltaTime

-0.15

Ãªnh

-0.14

akeup

-0.14

ÑĢÐ°Ñĩ

-0.14

 ÑģÑĤÑĢÐ°Ñħ

-0.14

lef

-0.14

wid

-0.14

lica

-0.14

POSITIVE LOGITS

åĶĲ

0.15

toy

0.15

ucc

0.15

cot

0.15

oad

0.14

ãģ¼

0.14

fad

0.14

Toy

0.14

Ð´ÐµÑĢ

0.14

æ¸Ĳ

0.13

Activations Density 0.435%

references to human experience and medical implications

No Comments

No Known Activations