INDEX

Explanations

key concepts related to support and relationships 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

cie

-0.15

olit

-0.15

Ep

-0.14

 æķ

-0.14

Ep

-0.14

chez

-0.14

chin

-0.14

Ã§a

-0.14

chine

-0.14

attery

-0.13

POSITIVE LOGITS

leÅ¾it

0.18

 showc

0.17

atoria

0.16

0.15

ntax

0.15

 milfs

0.14

 massaggi

0.14

}elseif

0.14

ssf

0.14

 cult

0.13

Activations Density 0.004%

key concepts related to support and relationships in various contexts

No Comments

No Known Activations