INDEX

Explanations

statistical terms and numerical values related to scores or performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

aat

-0.15

ponsive

-0.15

etros

-0.14

dden

-0.14

çºª

-0.13

/Peak

-0.13

.enumer

-0.13

 ÙħØ±Ø§Øª

-0.13

$MESS

-0.13

ãĥĶãĥ¼

-0.13

POSITIVE LOGITS

 Elim

0.24

 play

0.24

 Play

0.24

 elimination

0.23

play

0.23

 elimin

0.23

elim

0.23

 elim

0.22

 Round

0.22

 round

0.22

Activations Density 0.015%

statistical terms and numerical values related to scores or performance

No Comments

No Known Activations