INDEX

Explanations

phrases indicating direction or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

iw

-0.15

 Cyril

-0.15

lÃ¡

-0.15

zb

-0.15

uhl

-0.14

 Bowen

-0.14

íĭĢ

-0.14

yth

-0.14

abay

-0.14

cy

-0.13

POSITIVE LOGITS

enaire

0.16

orig

0.15

 Bark

0.14

 Deng

0.14

osi

0.14

avigate

0.14

osp

0.13

osate

0.13

pij

0.13

*pi

0.13

Activations Density 0.021%

phrases indicating direction or purpose

No Comments

No Known Activations