INDEX

Explanations

proper nouns associated with specific historical figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

antas

-0.15

getto

-0.14

icamente

-0.14

egov

-0.14

rych

-0.14

untime

-0.14

Ves

-0.14

 guys

-0.14

iet

-0.14

BuilderInterface

-0.14

POSITIVE LOGITS

edback

0.16

opper

0.15

Ð»Ð°Ð¼

0.14

asure

0.14

alic

0.14

 serialVersionUID

0.14

 horns

0.13

 fisse

0.13

azor

0.13

æ²ĸ

0.13

Activations Density 0.045%

proper nouns associated with specific historical figures

No Comments

No Known Activations