INDEX

Explanations

language related to job application processes and skills

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Hlav

-0.17

ibri

-0.16

arend

-0.16

ESIS

-0.16

à¥įà¤¯à¤µà¤¸

-0.15

malink

-0.15

KeyName

-0.15

 ëĭ¤ìļ´ë°Ľê¸°

-0.14

phia

-0.14

ores

-0.14

POSITIVE LOGITS

 code

0.25

 projects

0.22

 teams

0.21

 team

0.21

 coding

0.20

ä»£çłģ

0.20

 project

0.20

code

0.19

(code

0.19

Activations Density 0.560%

language related to job application processes and skills

No Comments

No Known Activations