INDEX

Explanations

references to championships or competitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

contres

-0.16

-0.15

amma

-0.15

iams

-0.15

resco

-0.15

hood

-0.14

uld

-0.14

à¸«à¸Ļ

-0.14

entication

-0.14

ÛĮØ´ÙĨ

-0.14

POSITIVE LOGITS

anova

0.19

OND

0.15

 ApiException

0.15

 prelim

0.14

wnd

0.14

PLICATION

0.14

-winning

0.14

ucha

0.13

Ø§Ø¹ÙĬ

0.13

áº£n

0.13

Activations Density 0.010%

references to championships or competitions

No Comments

No Known Activations