INDEX

Explanations

references to organizations, institutions, and their associated acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Ìĥ

-0.14

-0.13

 relevant

-0.13

 most

-0.13

emma

-0.13

Hav

-0.13

umb

-0.13

POSITIVE LOGITS

ÑįÑĤÐ¾Ð¼Ñĥ

0.20

odore

0.20

soever

0.19

phalt

0.19

 latter

0.18

adays

0.18

 arsch

0.17

.GPIO

0.17

HING

0.17

atre

0.17

Activations Density 0.455%

references to organizations, institutions, and their associated acronyms

No Comments

No Known Activations