INDEX

Explanations

references to digital object identifiers (DOIs) and scientific documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

.Automation

-0.18

ksam

-0.16

apel

-0.15

Æ°Æ¡ng

-0.15

.hs

-0.15

uluk

-0.15

eÄį

-0.15

 Marty

-0.15

ooter

-0.14

otland

-0.14

POSITIVE LOGITS

SSERT

0.16

0.14

?-

0.14

JD

0.14

 article

0.14

ã

0.14

/article

0.13

 è©ķ

0.13

 ange

0.13

Prompt

0.13

Activations Density 0.052%

references to digital object identifiers (DOIs) and scientific documentation

No Comments

No Known Activations