INDEX

Explanations

references to media appearances and interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oud

-0.17

rem

-0.15

 Prod

-0.15

 Broadcast

-0.14

 Productions

-0.14

olut

-0.14

 Staff

-0.14

Broadcast

-0.14

ategories

-0.14

\Bridge

-0.14

POSITIVE LOGITS

 Late

0.19

 TODAY

0.18

 COLORS

0.18

 Morning

0.17

 morning

0.17

Late

0.16

0.14

 Hannity

0.14

undi

0.14

udeau

0.14

Activations Density 0.138%

references to media appearances and interviews

No Comments

No Known Activations