INDEX

Explanations

sorting and ordering criteria related to data organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

INDER

-0.14

icha

-0.14

bris

-0.14

iband

-0.13

enza

-0.13

vise

-0.13

oad

-0.13

REEN

-0.13

inder

-0.13

POSITIVE LOGITS

 descending

0.40

asc

0.38

 DESC

0.37

 desc

0.36

 ascending

0.35

Descending

0.35

Asc

0.35

 descend

0.35

descending

0.34

ASC

0.34

Activations Density 0.028%

sorting and ordering criteria related to data organization

No Comments

No Known Activations