INDEX

Explanations

references to organizations and their roles in various contexts

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

jet

-0.15

Ã´

-0.15

 extreme

-0.14

ãģĴ

-0.14

Ã¶h

-0.14

bole

-0.14

onz

-0.13

 nÃ´ng

-0.13

olut

-0.13

 chill

-0.13

POSITIVE LOGITS

 activity

0.21

æ´»åĭķ

0.20

 Activity

0.19

 hoáº¡t

0.18

Activity

0.18

activity

0.18

 íĻľëıĻ

0.17

 æ´»

0.17

 activities

0.17

_ACTIVITY

0.17

Activations Density 0.073%

references to organizations and their roles in various contexts

No Comments

No Known Activations