INDEX

Explanations

references to specific products or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ife

-0.19

ÑĥÑĩ

-0.17

ink

-0.17

èģ

-0.16

IFE

-0.16

aub

-0.16

ubat

-0.16

ines

-0.16

 unsupported

-0.16

inky

-0.15

POSITIVE LOGITS

anco

0.19

elow

0.18

el

0.17

iras

0.16

ateur

0.16

ÑģÑĮ

0.16

ascar

0.15

ored

0.15

loy

0.15

ured

0.15

Activations Density 0.039%

references to specific products or brands

No Comments

No Known Activations