INDEX

Explanations

dates 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 rate

-0.16

Ñı

-0.16

 Rate

-0.15

Rate

-0.15

monic

-0.15

rate

-0.15

.rate

-0.15

_rate

-0.15

lek

-0.15

rowse

-0.15

POSITIVE LOGITS

istrovstvÃŃ

0.15

 setDescription

0.15

ç¾

0.14

¹Ħ

0.14

APT

0.14

ctest

0.14

 Conrad

0.14

.RGB

0.14

setProperty

0.14

volt

0.14

Activations Density 0.019%

dates and numerical information

No Comments

No Known Activations