INDEX

Explanations

phrases related to reasoning and making sense of complex situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ider

-0.15

coins

-0.14

inke

-0.14

GMEM

-0.14

ayacak

-0.13

 ?>"/>↵

-0.13

alim

-0.13

Æ°Æ¡ng

-0.13

 Kimberly

-0.13

anz

-0.13

POSITIVE LOGITS

 sense

0.56

 Sense

0.43

sense

0.42

Sense

0.40

 senses

0.35

 sentido

0.32

 sens

0.30

ense

0.23

 logical

0.21

SEN

0.20

Activations Density 0.021%

phrases related to reasoning and making sense of complex situations

No Comments

No Known Activations