INDEX

Explanations

references to fields and disciplines in medicine and engineering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

eton

-0.14

Nik

-0.14

ikh

-0.14

ighton

-0.14

strate

-0.13

ENC

-0.13

ackers

-0.13

ainer

-0.13

locker

-0.13

PILE

-0.13

POSITIVE LOGITS

 jadx

0.17

 preferredStyle

0.13

ims

0.13

Ø¨ÙĪØ§Ø³Ø·Ø©

0.13

ï¸

0.13

ebo

0.13

ologne

0.13

ãģłãģĳ

0.13

ustain

0.13

anford

0.13

Activations Density 0.004%

references to fields and disciplines in medicine and engineering

No Comments

No Known Activations