INDEX

Explanations

dates and numerical values in chronological order

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

achuset

-0.18

ÐºÑĢÐµÑĤ

-0.15

 creep

-0.15

abeth

-0.14

oldemort

-0.14

frei

-0.14

wart

-0.14

 turkey

-0.14

asar

-0.14

ÐĴÐ¡

-0.13

POSITIVE LOGITS

-spinner

0.15

oram

0.15

ÐµÑģÑĮ

0.15

pter

0.15

jective

0.14

/goto

0.14

á»

0.14

QualifiedName

0.14

iros

0.14

Subset

0.13

Activations Density 0.026%

dates and numerical values in chronological order

No Comments

No Known Activations