INDEX

Explanations

titles or headings related to health and medical news

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

stab

-0.18

Ðµ

-0.15

smith

-0.14

iteDatabase

-0.14

istrate

-0.14

ugin

-0.14

vor

-0.14

 geile

-0.13

atters

-0.13

umeric

-0.13

POSITIVE LOGITS

ensch

0.16

eln

0.15

DED

0.15

oky

0.15

ILING

0.14

(attribute

0.13

 Baron

0.13

ozilla

0.13

 Ð¿Ð¾Ð´Ð°

0.13

iffer

0.13

Activations Density 0.011%

titles or headings related to health and medical news

No Comments

No Known Activations