INDEX

Explanations

various forms of punctuation and discourse markers indicating dialogue or strong emotional expression

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

 Voor

-0.15

 Trim

-0.14

Vor

-0.14

 Ð¿Ð°ÑĢÐ°

-0.14

Logical

-0.14

'..

-0.13

 tert

-0.13

 Mehmet

-0.13

vor

-0.13

Tit

-0.13

POSITIVE LOGITS

thing

0.18

ukan

0.16

 Hodg

0.15

erna

0.15

ÂĿ

0.15

etz

0.15

Ú¯Ø§ÙĨ

0.15

aby

0.15

entence

0.14

åľ°ä¸ĭ

0.14

Activations Density 0.117%

various forms of punctuation and discourse markers indicating dialogue or strong emotional expression

No Comments

No Known Activations