INDEX

Explanations

terms related to academic and professional qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ncia

-0.17

CharArray

-0.16

Ð¾ÑıÑĤ

-0.15

nam

-0.15

Ĺı

-0.15

chia

-0.14

 Sherman

-0.14

Ã¼yÃ¼k

-0.14

argest

-0.14

PROP

-0.14

POSITIVE LOGITS

leigh

0.18

 UNESCO

0.16

uma

0.15

ÑĢÐµÑħ

0.15

 Favor

0.15

olas

0.14

 Lost

0.14

trace

0.14

olon

0.14

 trace

0.14

Activations Density 0.036%

terms related to academic and professional qualifications

No Comments

No Known Activations