INDEX

Explanations

questions and phrases emphasizing uncertainty or inquiry related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

otec

-0.18

igh

-0.17

ogui

-0.17

ishi

-0.17

IGH

-0.16

ighet

-0.16

etheus

-0.15

CLU

-0.15

><?

-0.15

NetMessage

-0.15

POSITIVE LOGITS

_Post

0.16

Â¯Â¯Â¯Â¯

0.15

unner

0.15

Ã¥l

0.15

rait

0.14

ypo

0.14

AIT

0.14

AIR

0.14

imizer

0.14

Activations Density 0.001%

questions and phrases emphasizing uncertainty or inquiry related to various subjects

No Comments

No Known Activations