INDEX

Explanations

terms associated with specific diseases and health-related topics

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

orm

-0.16

orno

-0.15

oined

-0.15

taire

-0.14

 Morm

-0.14

ÏĦÏī

-0.14

gger

-0.14

Ð»Ð°ÑĤ

-0.13

ÑĸÐ´Ð¾Ð¼

-0.13

POSITIVE LOGITS

va

0.16

 Gren

0.15

âĨ

0.14

 convictions

0.14

ypad

0.14

aar

0.14

REAK

0.14

blend

0.14

lang

0.13

endi

0.13

Activations Density 0.014%

terms associated with specific diseases and health-related topics

No Comments

No Known Activations