INDEX

Explanations

content related to food, dining, and culinary experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Abel

-0.16

Ã¼nst

-0.15

 yourselves

-0.15

env

-0.15

ku

-0.15

env

-0.15

 ÙĤØ¨

-0.14

IFY

-0.14

 Griff

-0.14

 Decompiled

-0.14

POSITIVE LOGITS

aca

0.15

İ·

0.15

vala

0.15

angles

0.15

fout

0.14

olk

0.14

Ð½Ð¾ÑģÑĤÑĮÑİ

0.14

Ð½Ð¾ÑģÑĤ

0.14

acha

0.14

umas

0.14

Activations Density 0.226%

content related to food, dining, and culinary experiences

No Comments

No Known Activations