INDEX

Explanations

expressions of value and appeal 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

tip

-0.18

bol

-0.15

Lad

-0.15

 equally

-0.14

rzy

-0.14

blr

-0.14

udder

-0.14

anford

-0.14

 relevant

-0.13

enÃŃ

-0.13

POSITIVE LOGITS

aight

0.15

elly

0.14

UCT

0.14

YO

0.14

ablish

0.13

noxious

0.13

iÅŁi

0.13

usta

0.13

 pÅĻeh

0.13

abase

0.13

Activations Density 0.102%

expressions of value and appeal related to various subjects

No Comments

No Known Activations