INDEX

Explanations

identifiers related to software components or programming functions

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

ynn

-0.17

omi

-0.16

aring

-0.15

Ã¡

-0.14

opi

-0.14

cy

-0.13

 chung

-0.13

ijn

-0.13

ogra

-0.13

 regul

-0.13

POSITIVE LOGITS

¸ı

0.17

leared

0.16

mando

0.15

eru

0.14

ì°¨

0.14

plies

0.14

inis

0.14

PLY

0.14

stial

0.13

âĻł

0.13

Activations Density 0.068%

identifiers related to software components or programming functions

No Comments

No Known Activations