INDEX

Explanations

references to testing and compatibility in technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÐµÐºÑĥ

-0.14

inson

-0.14

hci

-0.14

YRO

-0.14

asso

-0.14

iat

-0.14

 PureComponent

-0.13

ucer

-0.13

esc

-0.13

esk

-0.13

POSITIVE LOGITS

 audience

0.20

 Target

0.19

 targeting

0.19

 audiences

0.19

 target

0.19

target

0.19

-target

0.18

(Target

0.17

Target

0.17

 Audience

0.17

Activations Density 0.188%

references to testing and compatibility in technology

No Comments

No Known Activations