INDEX

Explanations

inquiries and requests for information related to various topics, particularly travel, products, and personal assistance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

tracts

-0.16

ayar

-0.15

ÑĨ

-0.15

ople

-0.14

 kdyby

-0.14

 cheers

-0.14

 Barnett

-0.13

strand

-0.13

caret

-0.13

dyby

-0.13

POSITIVE LOGITS

0.35

abase

0.19

ØŁ

0.17

ï¼Ł

0.17

à¥Ī?

0.17

but

0.17

but

0.17

ruz

0.16

?<

0.15

 yourself

0.15

Activations Density 0.061%

inquiries and requests for information related to various topics, particularly travel, products, and personal assistance

No Comments

No Known Activations