INDEX

Explanations

specific time stamps and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.20

agara

-0.20

agenta

-0.19

AGMA

-0.18

-0.17

 Coleman

-0.17

å¼µ

-0.17

 Mushroom

-0.16

anik

-0.16

POSITIVE LOGITS

0.47

0.29

0.24

0.22

0.21

0.20

0.18

Activations Density 0.013%

specific time stamps and numerical values

No Comments

No Known Activations