INDEX

Explanations

references to database filtering or querying in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rum

-0.15

reesome

-0.15

lsen

-0.14

ÐµÐ¼Ñĥ

-0.14

ÑĢÑĥÑĤ

-0.14

amins

-0.14

ÑģÑĤÑİ

-0.13

 kvinne

-0.13

POSITIVE LOGITS

ÑĤÑĮ

0.16

bpp

0.15

oard

0.15

 Ð§Ð¸

0.15

WARDED

0.15

anni

0.14

war

0.14

/vnd

0.14

Regs

0.14

 Warren

0.14

Activations Density 0.068%

references to database filtering or querying in code

No Comments

No Known Activations