INDEX

Explanations

negations and terms associated with conditions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

slack

-0.14

 Nack

-0.14

ATTER

-0.14

 useForm

-0.14

aron

-0.14

uos

-0.14

inar

-0.13

erna

-0.13

atter

-0.13

anda

-0.13

POSITIVE LOGITS

pas

0.42

PAS

0.32

Pas

0.31

Pas

0.31

pas

0.30

_pas

0.27

 pasa

0.22

 pÃ¡s

0.19

 jamais

0.19

gu

0.19

Activations Density 0.009%

negations and terms associated with conditions or states of being

No Comments

No Known Activations