INDEX

Explanations

concepts related to support and assistance 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

imates

-0.14

.infinity

-0.14

 Elekt

-0.14

.addTarget

-0.14

 ÄĲá»Ļ

-0.14

Ø§Ø³

-0.14

ÑŁ

-0.13

quam

-0.13

idget

-0.13

POSITIVE LOGITS

Dee

0.15

 Mild

0.15

_gb

0.14

 withdrawal

0.14

 Rich

0.14

à¹Ģà¸¢

0.14

 Sergeant

0.13

elin

0.13

atar

0.13

èĴĻ

0.13

Activations Density 0.135%

concepts related to support and assistance in various contexts

No Comments

No Known Activations