INDEX

Explanations

references to models or modeling techniques in discussions of systems and protocols

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

es

-0.20

ally

-0.16

fulness

-0.16

maal

-0.16

aches

-0.15

elig

-0.15

ptal

-0.15

ollow

-0.15

nal

-0.15

emin

-0.15

POSITIVE LOGITS

led

0.52

ë§ģ

0.25

LED

0.24

ocked

0.23

.addAttribute

0.21

/model

0.21

=model

0.20

agem

0.20

ers

0.20

ocking

0.19

Activations Density 0.037%

references to models or modeling techniques in discussions of systems and protocols

No Comments

No Known Activations