INDEX

Explanations

terms related to educational qualifications and professional experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

otos

-0.15

 è©

-0.14

imos

-0.14

elib

-0.14

hatt

-0.14

-extension

-0.13

 âĨĴ↵↵

-0.13

æĶ¶å½ķ

-0.13

ObjectContext

-0.13

_itr

-0.13

POSITIVE LOGITS

 leadership

0.29

 Leadership

0.25

leaders

0.24

 human

0.23

 marketing

0.22

 strategic

0.22

Leaders

0.21

 Human

0.20

 management

0.20

 succession

0.19

Activations Density 0.198%

terms related to educational qualifications and professional experience

No Comments

No Known Activations