INDEX

Explanations

terms related to viruses and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Î»Î®

-0.16

lett

-0.15

ÐµÑĢÐµÑĩ

-0.15

FOR

-0.15

)test

-0.14

 jenter

-0.14

é¼

-0.14

bsite

-0.14

amm

-0.14

POSITIVE LOGITS

 Pruitt

0.16

Ø¨Ø§ÙĨ

0.16

ymes

0.14

 Malk

0.14

dives

0.14

riott

0.14

hou

0.14

Å

0.14

į

0.13

OwnerId

0.13

Activations Density 0.017%

terms related to viruses and their classifications

No Comments

No Known Activations