INDEX

Explanations

references to adaptations or adaptations based on original works, including novels and screenplays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

entlich

-0.16

 cÃ©lib

-0.15

èĹı

-0.14

é±

-0.14

QQ

-0.14

 ActionTypes

-0.14

ħĮ

-0.14

anship

-0.14

ammad

-0.14

iltr

-0.13

POSITIVE LOGITS

locker

0.15

Unt

0.15

unt

0.14

 Gene

0.14

aims

0.14

Cir

0.14

 iter

0.13

aired

0.13

Conference

0.13

Cf

0.13

Activations Density 0.020%

references to adaptations or adaptations based on original works, including novels and screenplays

No Comments

No Known Activations