INDEX

Explanations

titles and descriptions relating to health and wellness literature

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Lobby

-0.16

cao

-0.14

ddit

-0.14

iye

-0.14

helm

-0.14

AO

-0.13

hatt

-0.13

anske

-0.13

URRENCY

-0.13

lander

-0.13

POSITIVE LOGITS

unkt

0.15

 dereg

0.15

ropa

0.14

ë¡Ŀ

0.14

andi

0.14

ummer

0.13

ãģİ

0.13

 Sass

0.13

 prez

0.13

å·»

0.13

Activations Density 0.200%

titles and descriptions relating to health and wellness literature

No Comments

No Known Activations

titles and descriptions relating to health and wellness literature

No Comments

No Known Activations