INDEX

Explanations

metrics and statistics indicating performance or achievements

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

.scalablytyped

-0.13

Ã¼nden

-0.12

ë¦¬ë¡ľ

-0.10

 à¸ģà¸£à¸ģ

-0.10

ekler

-0.10

lfw

-0.10

ÂłBf

-0.10

ÃŃÅ¡

-0.10

enegro

-0.10

ulfilled

-0.10

POSITIVE LOGITS

in

1.09

Âłin

0.60

in

0.58

åľ¨

0.56

in

0.52

 ÙģÙĬ

0.50

_in

0.47

-in

0.47

 åľ¨

0.47

à¹ĥà¸Ļ

0.47

Activations Density 2.692%

metrics and statistics indicating performance or achievements

No Comments

No Known Activations