INDEX

Explanations

references to spam and spam-related issues

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

umble

-0.16

entanyl

-0.15

ean

-0.15

ollo

-0.15

 plÃ¡

-0.14

ocus

-0.14

zan

-0.14

ÑĭÐ²Ð°

-0.13

usz

-0.13

jem

-0.13

POSITIVE LOGITS

ATAB

0.16

 Vinci

0.16

ernet

0.15

åĬĽçļĦ

0.15

buz

0.15

NCY

0.15

 masc

0.14

nosti

0.14

ayar

0.14

emachine

0.14

Activations Density 0.007%

references to spam and spam-related issues

No Comments

No Known Activations