INDEX

Explanations

spatial relationships and positioning of objects or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

kem

-0.18

 Ridley

-0.15

ani

-0.15

ontent

-0.14

ANI

-0.14

bil

-0.14

Ø§ÙĨÛĮ

-0.14

otent

-0.14

 Addison

-0.14

 scal

-0.14

POSITIVE LOGITS

 Crate

0.16

ÃŃas

0.15

ioxide

0.15

æĸ¹

0.14

rais

0.14

Ð¾ÑĩÐºÐ¸

0.14

erland

0.14

ÐµÐ½Ð·

0.14

Trivia

0.14

Activations Density 0.115%

spatial relationships and positioning of objects or features

No Comments

No Known Activations