INDEX

Explanations

questions and phrases focused on understanding methods, processes, and outcomes

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

zek

-0.18

educt

-0.16

äºľ

-0.15

geois

-0.15

zens

-0.15

umen

-0.14

opia

-0.14

lum

-0.14

reece

-0.14

POSITIVE LOGITS

ninger

0.17

Î´Î·

0.15

acet

0.15

ologne

0.14

ichni

0.14

 ÐļÑĢÐ°

0.14

elsen

0.14

pring

0.14

Wak

0.14

hint

0.14

Activations Density 0.077%

questions and phrases focused on understanding methods, processes, and outcomes

No Comments

No Known Activations