INDEX

Explanations

names or references to prominent individuals or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 extremes

-0.15

 Vern

-0.15

 Epid

-0.14

chn

-0.14

DAL

-0.14

ses

-0.14

emple

-0.14

 chÃ¢u

-0.14

/share

-0.14

fal

-0.13

POSITIVE LOGITS

peare

0.19

Ø²Ø§Ø¯Ùĩ

0.17

baz

0.16

apult

0.15

akespeare

0.15

iÃŃ

0.15

eldon

0.15

afs

0.15

eneg

0.15

Activations Density 0.024%

names or references to prominent individuals or figures

No Comments

No Known Activations