INDEX

Explanations

code updates or changes in technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 metall

-0.17

ohon

-0.15

sequ

-0.15

OrCreate

-0.14

ivre

-0.14

Ø§Øº

-0.14

ailer

-0.14

å°º

-0.14

cctor

-0.14

 togg

-0.13

POSITIVE LOGITS

getto

0.14

artz

0.14

"urls

0.14

ä¸ĢçĤ¹

0.13

igon

0.13

iem

0.13

rat

0.13

otionEvent

0.13

onestly

0.13

Activations Density 0.027%

code updates or changes in technical documents

No Comments

No Known Activations