INDEX

Explanations

words related to discussions or decisions made about items or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Millet

-0.19

_MINUS

-0.18

Ã¡zd

-0.16

raÅ¾

-0.16

iman

-0.15

MediaType

-0.15

SSERT

-0.15

kes

-0.14

Ø§ÙģÙĤ

-0.14

ugo

-0.14

POSITIVE LOGITS

 more

0.54

mor

0.47

 More

0.41

more

0.41

mo

0.39

 mÃ¡s

0.37

 mehr

0.37

More

0.36

_more

0.35

-more

0.35

Activations Density 0.190%

words related to discussions or decisions made about items or choices

No Comments

No Known Activations