INDEX

Explanations

structural or organizational elements in the text, often related to parentheses or grouped information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

zk

-0.17

 cÃ©lib

-0.15

Intialized

-0.15

ewolf

-0.15

eward

-0.15

ÄĽÅ¾

-0.15

BitFields

-0.15

wj

-0.14

MemoryWarning

-0.14

BackingField

-0.13

POSITIVE LOGITS

avec

0.28

Ãł

0.27

les

0.26

Ã©t

0.26

voir

0.26

rÃ©

0.25

contre

0.25

ouver

0.25

une

0.25

chez

0.24

Activations Density 0.050%

structural or organizational elements in the text, often related to parentheses or grouped information

No Comments

No Known Activations