INDEX

Explanations

individuals associated with specific roles or accomplishments in their fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oman

-0.16

ADO

-0.14

zd

-0.14

re

-0.13

ilage

-0.13

 ÐºÐ°Ð±

-0.13

 hood

-0.13

Bea

-0.13

 activ

-0.13

avÄĽ

-0.13

POSITIVE LOGITS

 Weinstein

0.16

à¥Įà¤¦

0.16

umu

0.15

avl

0.15

ojÃŃ

0.15

ãĥ³ãĥĳ

0.15

iyel

0.15

 meiden

0.14

oklyn

0.14

Ð¸ÑĤÐ¸

0.14

Activations Density 0.532%

individuals associated with specific roles or accomplishments in their fields

No Comments

No Known Activations