INDEX

Explanations

references to specific types of organizations and events related to biology or health

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

afone

-0.16

ivol

-0.16

Ã£ng

-0.15

ulate

-0.15

yleft

-0.15

pee

-0.14

omat

-0.14

kola

-0.14

arrass

-0.14

enerator

-0.14

POSITIVE LOGITS

eker

0.14

 máº¯t

0.14

 governed

0.14

OUN

0.13

 ware

0.13

 BAÅŀ

0.13

elines

0.13

getter

0.13

 cons

0.13

Activations Density 0.833%

references to specific types of organizations and events related to biology or health

No Comments

No Known Activations