INDEX

Explanations

terms related to professionalism and professional roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ã¤ter

-0.16

ajan

-0.16

boarding

-0.16

hole

-0.16

Ìĥ

-0.15

ÐµÑĢÐ¾

-0.15

asha

-0.14

lessly

-0.14

ãĤĪãģĨãģª

-0.14

orian

-0.14

POSITIVE LOGITS

-grade

0.31

ized

0.29

ization

0.28

izing

0.25

ising

0.25

ism

0.24

ised

0.24

izes

0.24

isation

0.23

ize

0.23

Activations Density 0.026%

terms related to professionalism and professional roles

No Comments

No Known Activations