INDEX

Explanations

expressions of comparison or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

yled

-0.15

enade

-0.14

anter

-0.14

äºĭæ¥Ń

-0.14

oy

-0.13

ç·´

-0.13

wal

-0.13

ayer

-0.13

Others

-0.13

åĢī

-0.13

POSITIVE LOGITS

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.20

Lal

0.16

0.15

lec

0.15

utive

0.14

ÄŁ

0.14

efa

0.14

ependency

0.14

arp

0.14

 case

0.14

Activations Density 0.081%

expressions of comparison or similarity

No Comments

No Known Activations