INDEX

Explanations

references to related news articles or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-0.15

pcs

-0.14

çĬ¯

-0.14

pty

-0.14

Ìģ

-0.14

awner

-0.14

cs

-0.14

 Mall

-0.14

AVL

-0.14

Ã¡cil

-0.14

POSITIVE LOGITS

trer

0.16

-NLS

0.15

Ð±ÑĥÐ´ÑĮ

0.15

PointerException

0.15

uddy

0.14

auer

0.14

WISE

0.14

æľĭ

0.14

uco

0.14

anst

0.14

Activations Density 0.114%

references to related news articles or updates

No Comments

No Known Activations