INDEX

Explanations

references to inclusivity across various contexts and sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Newspaper

-0.16

obao

-0.15

Ply

-0.15

smith

-0.14

antas

-0.14

ichen

-0.14

alama

-0.14

ired

-0.14

åĳ½

-0.14

ÙĬØªÙĬ

-0.13

POSITIVE LOGITS

Ã¡f

0.15

ancel

0.15

umin

0.14

igator

0.13

istra

0.13

zell

0.13

 Resolve

0.13

 deniz

0.13

toc

0.13

uckets

0.13

Activations Density 0.230%

references to inclusivity across various contexts and sectors

No Comments

No Known Activations