INDEX

Explanations

terms related to theoretical concepts and methodologies in scientific discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

kening

-0.17

ç´ł

-0.16

å¾

-0.16

aire

-0.15

ensburg

-0.15

idon

-0.14

Ã¶k

-0.14

 Dana

-0.14

POSITIVE LOGITS

esch

0.15

ì¹Ń

0.15

 Lauderdale

0.15

amp

0.14

ye

0.14

anned

0.14

egin

0.14

Ð¾Ð»Ð¾Ð²

0.14

elastic

0.14

elsey

0.14

Activations Density 0.038%

terms related to theoretical concepts and methodologies in scientific discussions

No Comments

No Known Activations