INDEX

Explanations

references to mathematical concepts and power laws

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

_fft

-0.14

 pigment

-0.14

dirs

-0.14

 frequencies

-0.13

 Quaternion

-0.13

abay

-0.13

ango

-0.13

 ortalama

-0.13

POSITIVE LOGITS

 curve

0.38

 Curve

0.33

curve

0.31

 curves

0.31

Curve

0.30

 slope

0.30

_curve

0.28

 linear

0.28

urve

0.27

slope

0.26

Activations Density 0.206%

references to mathematical concepts and power laws

No Comments

No Known Activations