INDEX

Explanations

numerical values and references to fundamental concepts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ahlen

-0.15

idge

-0.15

ensen

-0.15

ÙģØ©

-0.14

 diseÃ±ador

-0.14

ÑĩÐ°Ð¹

-0.14

hari

-0.14

hart

-0.14

vard

-0.14

inu

-0.14

POSITIVE LOGITS

atten

0.15

Ð·Ð°Ð±

0.15

 Hakk

0.14

atte

0.14

Elf

0.14

ibi

0.13

Ð»Ð°Ð´Ð°

0.13

isoft

0.13

 Bott

0.13

STYPE

0.13

Activations Density 0.083%

numerical values and references to fundamental concepts in various contexts

No Comments

No Known Activations