INDEX

Explanations

code-related definitions and preprocessor directives

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

pus

-0.15

ymes

-0.15

 fast

-0.14

auga

-0.14

Ã¡li

-0.14

 tender

-0.13

getic

-0.13

cies

-0.13

aras

-0.13

 blew

-0.13

POSITIVE LOGITS

roph

0.16

Äįi

0.16

 phá»ĳi

0.15

 CONTRIBUTORS

0.15

Ã±ana

0.14

 defaultCenter

0.14

venir

0.14

Dal

0.14

(_.

0.14

-widgets

0.13

Activations Density 0.002%

code-related definitions and preprocessor directives

No Comments

No Known Activations