INDEX

Explanations

references to class sizes and educational metrics

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

 lengths

-0.19

 widths

-0.19

 heights

-0.18

 shortened

-0.18

*width

-0.17

-width

-0.17

width

-0.17

(length

-0.17

 distances

-0.16

 widest

-0.16

POSITIVE LOGITS

 size

0.53

size

0.48

-size

0.46

.size

0.45

_size

0.43

 Size

0.42

	size

0.41

Size

0.41

 SIZE

0.38

å¤§å°ı

0.37

Activations Density 0.093%

references to class sizes and educational metrics

No Comments

No Known Activations