INDEX

Explanations

technical terms related to software dependencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

prs

-0.15

mite

-0.15

 Sanchez

-0.14

benh

-0.14

olla

-0.14

aras

-0.14

 Higgins

-0.14

 èĩªåĬ¨çĶŁæĪĲ

-0.14

 Sche

-0.14

à¸£à¸ĵ

-0.14

POSITIVE LOGITS

0.15

 Berm

0.14

 PROPERTY

0.14

¶Ī

0.13

icom

0.13

 Beste

0.13

 base

0.13

Activations Density 0.013%

technical terms related to software dependencies

No Comments

No Known Activations