INDEX

Explanations

statistical data and numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

@student

-0.16

usercontent

-0.16

anche

-0.15

 HÃ¬nh

-0.15

lify

-0.15

oner

-0.15

ULER

-0.14

æµ©

-0.14

ter

-0.14

eme

-0.14

POSITIVE LOGITS

ãĥ«ãĤ¯

0.16

zap

0.15

otyping

0.14

tainment

0.14

olet

0.14

yellow

0.13

xed

0.13

ubar

0.13

 Elder

0.13

Å¾

0.13

Activations Density 0.057%

statistical data and numerical information

No Comments

No Known Activations