INDEX

Explanations

references to specific answers or responses in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ã¡i

-0.18

kes

-0.15

fin

-0.15

press

-0.15

 spec

-0.14

 bush

-0.14

 famously

-0.14

ëĭ¨ì²´

-0.14

ef

-0.14

xford

-0.14

POSITIVE LOGITS

slashes

0.16

SOLE

0.16

cales

0.15

cente

0.15

InlineData

0.15

soles

0.15

reserve

0.15

nable

0.15

-Sah

0.15

 ComVisible

0.14

Activations Density 0.049%

references to specific answers or responses in a discussion

No Comments

No Known Activations