INDEX

Explanations

key concepts related to importance and relevance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

enco

-0.19

 crow

-0.16

AGMA

-0.16

á»Ń

-0.16

agma

-0.15

esco

-0.15

ARSE

-0.15

mtx

-0.15

.jasper

-0.14

uluk

-0.14

POSITIVE LOGITS

ypass

0.15

atten

0.15

 abst

0.14

cean

0.14

 meteor

0.14

illian

0.14

andal

0.14

react

0.14

ogne

0.14

 convertible

0.14

Activations Density 0.314%

key concepts related to importance and relevance

No Comments

No Known Activations