INDEX

Explanations

references to the Atlantic region or entities associated with it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Ø§Ø©

-0.16

jvu

-0.16

gings

-0.15

geois

-0.15

oppins

-0.15

ingen

-0.15

jte

-0.15

ç¿Ķ

-0.15

 nues

-0.14

dess

-0.14

POSITIVE LOGITS

-Pacific

0.21

antic

0.18

mour

0.16

 slave

0.15

 Highlands

0.15

ism

0.15

 Ocean

0.15

ismus

0.15

antics

0.14

 Wolff

0.14

Activations Density 0.012%

references to the Atlantic region or entities associated with it

No Comments

No Known Activations