INDEX

Explanations

instances of connection phrases indicating relationships or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

mers

-0.17

leta

-0.16

omens

-0.15

æ³°

-0.14

ients

-0.14

zano

-0.14

Ã¡ch

-0.13

agma

-0.13

Ã¶m

-0.13

erialize

-0.13

POSITIVE LOGITS

although

0.17

upa

0.15

 although

0.15

ushman

0.14

Å¼y

0.14

OO

0.13

isin

0.13

antes

0.13

it

0.13

this

0.13

Activations Density 0.338%

instances of connection phrases indicating relationships or sequences

No Comments

No Known Activations