INDEX

Explanations

numerical values related to statistics or performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.19

esto

-0.18

holm

-0.17

alg

-0.16

villa

-0.16

BJ

-0.15

olland

-0.15

 å©

-0.15

loff

-0.15

POSITIVE LOGITS

StandardItem

0.16

 Cond

0.15

 cond

0.15

 Canal

0.15

sik

0.14

 Schul

0.14

YP

0.13

 EXEMPLARY

0.13

iane

0.13

lander

0.13

Activations Density 0.022%

numerical values related to statistics or performance metrics

No Comments

No Known Activations