INDEX

Explanations

expressions related to troubleshooting and problem-solving 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 @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

jas

-0.16

essed

-0.15

hee

-0.15

ä¸įäºĨ

-0.14

.ali

-0.14

DEFAULT

-0.14

McB

-0.14

TAG

-0.14

Ey

-0.14

 Wolfgang

-0.14

POSITIVE LOGITS

reur

0.17

cko

0.16

UGH

0.16

å§¿

0.16

erator

0.16

ocene

0.15

 Morse

0.15

oose

0.15

ulus

0.15

uml

0.14

Activations Density 0.063%

expressions related to troubleshooting and problem-solving in various contexts

No Comments

No Known Activations