INDEX

Explanations

references to significant legal events and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 critical

-0.15

eniable

-0.14

urtle

-0.14

rome

-0.14

.weixin

-0.14

oren

-0.13

letcher

-0.13

ustos

-0.13

 Carson

-0.13

Critical

-0.13

POSITIVE LOGITS

ju

0.16

yu

0.15

chal

0.14

atte

0.14

unma

0.14

CompleteListener

0.14

dal

0.14

endi

0.13

-errors

0.13

emann

0.13

Activations Density 0.297%

references to significant legal events and their implications

No Comments

No Known Activations