INDEX

Explanations

references to papal documents and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ãĥ³ãĥĩãĤ£

-0.18

abant

-0.15

oun

-0.15

undos

-0.14

ells

-0.14

 Sequential

-0.14

yn

-0.14

 Hulk

-0.14

 Sans

-0.14

IGH

-0.14

POSITIVE LOGITS

ARIO

0.16

enek

0.15

dao

0.15

izard

0.15

ternet

0.14

ÑĤÐ°Ð»

0.14

ç¯

0.14

ario

0.14

sher

0.13

 lÃŃ

0.13

Activations Density 0.019%

references to papal documents and figures

No Comments

No Known Activations