INDEX

Explanations

references to different sections or components of music, products, or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð±Ð°Ñĩ

-0.15

ISM

-0.14

Ð³Ñĥ

-0.14

anyl

-0.14

urs

-0.14

bac

-0.14

 æīĢ

-0.14

istrat

-0.13

.bs

-0.13

irs

-0.13

POSITIVE LOGITS

shit

0.17

yun

0.15

opis

0.15

æĮ

0.14

è¨Ĭ

0.14

oog

0.14

eland

0.14

é¢¨

0.14

zn

0.13

haul

0.13

Activations Density 0.274%

references to different sections or components of music, products, or experiences

No Comments

No Known Activations