INDEX

Explanations

terms related to academic policies and procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÌĨ

-0.16

ogl

-0.15

levation

-0.14

ãģŀ

-0.14

elves

-0.14

.openg

-0.14

amation

-0.13

ÄĲT

-0.13

LEMENT

-0.13

POSITIVE LOGITS

à¤¾↵

0.14

:animated

0.14

 Erotische

0.13

adiens

0.13

fills

0.12

èİī

0.12

:async

0.12

serie

0.12

-Series

0.12

 helicopt

0.12

Activations Density 0.095%

terms related to academic policies and procedures

No Comments

No Known Activations