INDEX

Explanations

cooking actions and instructions related to food preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

achten

-0.17

ault

-0.16

 aktu

-0.15

ICE

-0.15

-Jul

-0.15

immel

-0.14

ethe

-0.14

etable

-0.14

ugu

-0.14

POSITIVE LOGITS

sey

0.14

.raise

0.14

andal

0.14

lanma

0.13

Timeline

0.13

eur

0.13

ampoo

0.13

jang

0.13

ãĥĶãĥ¼

0.13

æī«

0.13

Activations Density 0.007%

cooking actions and instructions related to food preparation

No Comments

No Known Activations