INDEX

Explanations

terms related to neurology and its various specializations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð½ÑĸÐ²ÐµÑĢ

-0.16

oop

-0.15

CTIONS

-0.14

æ¼ı

-0.14

revision

-0.14

 Aust

-0.14

ansson

-0.14

isk

-0.14

moil

-0.14

-0.13

POSITIVE LOGITS

atto

0.16

0.15

 plÃ¡

0.14

 Coleman

0.14

 DbSet

0.14

ially

0.14

ger

0.14

omal

0.14

ucht

0.13

 SqlDataReader

0.13

Activations Density 0.007%

terms related to neurology and its various specializations

No Comments

No Known Activations