INDEX

Explanations

structured elements and metadata in academic articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.18

ude

-0.17

Ð´Ð¾Ð½

-0.16

zell

-0.15

 ä»£

-0.15

cplusplus

-0.15

.CR

-0.15

ARRANT

-0.14

reck

-0.14

å¿

-0.14

POSITIVE LOGITS

ombo

0.19

Weg

0.16

0.15

ffen

0.15

}elseif

0.14

istribute

0.14

ivos

0.14

 treating

0.14

itan

0.14

egl

0.14

Activations Density 0.016%

structured elements and metadata in academic articles

No Comments

No Known Activations