INDEX

Explanations

references to wheels and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

uzzer

-0.17

Ä±rak

-0.15

ureau

-0.14

amilia

-0.14

uggle

-0.14

resco

-0.14

allen

-0.14

 Ulus

-0.14

ushman

-0.14

itchen

-0.14

POSITIVE LOGITS

awah

0.16

 diameter

0.16

assage

0.15

hack

0.15

ring

0.15

backs

0.14

RF

0.14

inia

0.14

ylie

0.13

Activations Density 0.013%

references to wheels and related terms

No Comments

No Known Activations