INDEX

Explanations

relationships and actions among individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.15

ibold

-0.15

chedulers

-0.14

isposable

-0.14

 Idle

-0.13

raya

-0.13

ienne

-0.13

ÑĢÐ¸Ð·

-0.13

POSITIVE LOGITS

 Setter

0.16

 serialVersionUID

0.16

VisualStyle

0.16

ä»¥å¤ĸ

0.15

 aside

0.15

 incident

0.14

amente

0.13

olm

0.13

 Daly

0.13

 alone

0.13

Activations Density 0.213%

relationships and actions among individuals

No Comments

No Known Activations