INDEX

Explanations

reported speech or quotations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ccd

-0.14

empo

-0.14

lod

-0.14

 humid

-0.14

lope

-0.14

ÎµÎ¹

-0.13

 mand

-0.13

Ø³Ùħ

-0.13

WR

-0.13

ossil

-0.13

POSITIVE LOGITS

ÅĻeba

0.15

ascus

0.14

isle

0.14

mour

0.14

endas

0.14

bih

0.14

.onViewCreated

0.14

atti

0.14

fillType

0.14

oul

0.14

Activations Density 0.043%

reported speech or quotations within the text

No Comments

No Known Activations