INDEX

Explanations

references to academic articles and publications

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

sey

-0.16

 connector

-0.14

wind

-0.14

shaw

-0.14

Ñĵ

-0.14

regor

-0.14

leitung

-0.14

heat

-0.14

 Hurt

-0.14

 heat

-0.13

POSITIVE LOGITS

xbb

0.15

Zuk

0.15

á»ĳc

0.15

 éĸ

0.13

 crim

0.13

xbd

0.13

RuntimeException

0.13

elden

0.13

UNDER

0.13

ouz

0.13

Activations Density 0.014%

references to academic articles and publications

No Comments

No Known Activations