INDEX

Explanations

terms related to hair type, texture, and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

wie

-0.15

)prepare

-0.15

ebra

-0.15

ulta

-0.15

ulings

-0.14

ungs

-0.14

 Procedure

-0.14

 CrossAxisAlignment

-0.13

OTES

-0.13

POSITIVE LOGITS

ega

0.16

EGA

0.16

acons

0.16

SPATH

0.15

ipe

0.15

idor

0.15

.inf

0.15

ERO

0.14

ahn

0.13

Î½Ïī

0.13

Activations Density 0.156%

terms related to hair type, texture, and characteristics

No Comments

No Known Activations