INDEX

Explanations

numerical data or references to dates and statistics

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

imm

-0.17

-0.16

ability

-0.15

redo

-0.15

 immersion

-0.15

ov

-0.15

anda

-0.15

 negot

-0.14

edia

-0.14

POSITIVE LOGITS

ynes

0.19

 GOODMAN

0.15

avage

0.14

ìŁģ

0.14

RetVal

0.14

unning

0.14

libft

0.14

à¹Īà¸³

0.13

asil

0.13

Ð³Ð°Ð»Ñĸ

0.13

Activations Density 0.077%

numerical data or references to dates and statistics

No Comments

No Known Activations