INDEX

Explanations

numerical data and figures, particularly in context with locations and services

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

-0.29

-0.28

"'

-0.23

\`

-0.21

'O

-0.20

"[

-0.20

'm

-0.20

'll

-0.20

'hui

-0.20

"\

-0.20

POSITIVE LOGITS

–

0.19

0.16

–

0.15

âĪĴ

0.15

 ÐµÑīÑĳ

0.14

ku

0.14

 âĪĴ

0.14

’h

0.14

Activations Density 0.120%

numerical data and figures, particularly in context with locations and services

No Comments

No Known Activations