INDEX

Explanations

keywords and metadata related to research studies and medical articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 thanks

-0.17

 Thanks

-0.17

 Others

-0.15

Ã¤Ã¤

-0.14

/examples

-0.14

uche

-0.14

Thanks

-0.14

Others

-0.14

 OTHER

-0.14

 Higgins

-0.14

POSITIVE LOGITS

 Kaplan

0.17

 Severity

0.15

/GPL

0.15

 Humans

0.15

estion

0.15

 question

0.14

 ìĦľìļ¸íĬ¹ë³Ħìĭľ

0.14

von

0.14

 United

0.14

Activations Density 0.004%

keywords and metadata related to research studies and medical articles

No Comments

No Known Activations