INDEX

Explanations

references to numerical data or accession numbers in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ISIBLE

-0.17

keit

-0.16

çĽĳåĲ¬é¡µéĿ¢

-0.15

.fromString

-0.15

ymce

-0.14

eview

-0.14

á»ĵi

-0.14

roll

-0.14

 longer

-0.14

Hav

-0.14

POSITIVE LOGITS

 Bang

0.14

 wrought

0.14

fa

0.14

mania

0.14

 Sheridan

0.13

 Bruins

0.13

akh

0.13

ÑĢÐ¾Ð¿

0.13

TI

0.13

 piger

0.13

Activations Density 0.046%

references to numerical data or accession numbers in a research context

No Comments

No Known Activations