INDEX

Explanations

specific addresses and location details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

unik

-0.18

 ADDR

-0.17

aber

-0.17

ibus

-0.17

dere

-0.15

éĢ

-0.14

minate

-0.14

uzzer

-0.14

_pixel

-0.14

ogy

-0.14

POSITIVE LOGITS

 Milwaukee

0.34

Mil

0.24

waukee

0.24

aukee

0.21

 Brewers

0.20

0.19

mil

0.17

ZF

0.17

mil

0.15

odal

0.15

Activations Density 0.024%

specific addresses and location details

No Comments

No Known Activations