INDEX

Explanations

references to participant responsibilities and restrictions regarding agreements

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

SOR

-0.17

ampus

-0.14

odos

-0.14

Ð¼ÐµÐ½Ð°

-0.13

ornings

-0.13

áº©n

-0.13

éĩįçĤ¹

-0.13

olatile

-0.13

/high

-0.13

 fair

-0.13

POSITIVE LOGITS

nor

0.25

 unless

0.23

nor

0.22

any

0.21

 anything

0.19

Nor

0.18

è¶ħè¿ĩ

0.18

ä»»ä½ķ

0.17

 ever

0.17

unless

0.17

Activations Density 0.155%

references to participant responsibilities and restrictions regarding agreements

No Comments

No Known Activations