INDEX

Explanations

references to the reader or audience, particularly in a direct and engaging manner

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

ÑĮÑı

-0.17

orio

-0.16

arty

-0.16

asy

-0.15

aph

-0.14

cr

-0.14

branch

-0.14

Ø²Ø§Ø±

-0.14

POSITIVE LOGITS

Ð¸ÑĤÐ¾Ð²

0.15

èĴ

0.15

ropa

0.14

plete

0.14

uien

0.14

(strtolower

0.14

ijke

0.14

ÏĮÎ´

0.14

hist

0.14

iatrics

0.14

Activations Density 0.013%

references to the reader or audience, particularly in a direct and engaging manner

No Comments

No Known Activations