INDEX

Explanations

numerical information and references to sections or parts within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

é¼

-0.15

.googleapis

-0.15

anova

-0.14

aucoup

-0.14

ÑħÐ°

-0.14

lero

-0.13

Ã©rt

-0.13

POSITIVE LOGITS

ÐºÐ°Ñģ

0.15

'gc

0.14

Tab

0.14

unn

0.13

ethod

0.13

ewis

0.13

ÑĨÐµÑģ

0.13

 INCIDENT

0.13

poser

0.13

/slider

0.13

Activations Density 0.036%

numerical information and references to sections or parts within a document

No Comments

No Known Activations