INDEX

Explanations

terms related to academic and clinical subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 escorte

-0.13

/entities

-0.12

Ø´ÙħØ§ÙĦÛĮ

-0.12

rvÃ©

-0.12

Ø¯ÛĮÚ¯Ø±

-0.12

.OnClickListener

-0.11

 trÃº

-0.11

PackageManager

-0.11

 begr

-0.10

 conseils

-0.10

POSITIVE LOGITS

ittest

0.13

unma

0.13

antanamo

0.13

venge

0.12

ilogy

0.12

meli

0.12

âķĿ

0.12

/*č↵

0.12

vell

0.12

 (“

0.12

Activations Density 0.016%

terms related to academic and clinical subjects

No Comments

No Known Activations