INDEX

Explanations

instances of hesitation or uncertainty in conversation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Swords

-0.16

Ð·ÑĮ

-0.14

.bz

-0.14

æ¹

-0.14

Ã³b

-0.14

Ø³Ø±

-0.14

ì§¸

-0.14

aris

-0.14

Ð½Ð°Ð´

-0.14

dac

-0.14

POSITIVE LOGITS

otre

0.15

 Friedrich

0.14

nton

0.14

odium

0.14

*)_

0.13

linger

0.13

 indul

0.13

oth

0.13

cassert

0.13

utenberg

0.13

Activations Density 0.061%

instances of hesitation or uncertainty in conversation

No Comments

No Known Activations