INDEX

Explanations

references to the English language and its proficiency levels

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

ØµÙģ

-0.18

aceutical

-0.16

aday

-0.15

tura

-0.15

achel

-0.15

naments

-0.15

ince

-0.14

SetActive

-0.14

iterals

-0.14

 serialVersionUID

-0.14

POSITIVE LOGITS

toISOString

0.15

-speaking

0.15

 Midlands

0.15

spe

0.15

 Wing

0.15

velop

0.14

YE

0.14

esi

0.14

ĸī

0.14

man

0.14

Activations Density 0.012%

references to the English language and its proficiency levels

No Comments

No Known Activations