INDEX

Explanations

references to administrative decisions and actions related to student issues and incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

eras

-0.17

ÎºÎ·ÏĤ

-0.15

ollo

-0.15

_targets

-0.14

 Overse

-0.14

UNU

-0.14

è¦³

-0.14

æľį

-0.14

FTA

-0.14

Van

-0.13

POSITIVE LOGITS

lates

0.14

DIC

0.14

ATCH

0.14

¥Ĳ

0.14

cow

0.14

contents

0.14

ë§Ī

0.13

 Dana

0.13

ustin

0.13

AGES

0.13

Activations Density 0.018%

references to administrative decisions and actions related to student issues and incidents

No Comments

No Known Activations