INDEX

Explanations

mathematical expressions and notations associated with dimensionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Pregn

-0.15

 pregnant

-0.14

anno

-0.14

avis

-0.13

rog

-0.13

 pregnancy

-0.13

arrant

-0.13

ReuseIdentifier

-0.13

 Pregnancy

-0.13

POSITIVE LOGITS

0.40

0.33

-k

0.25

âĪĴ

0.23

-j

0.21

+k

0.21

-l

0.20

-i

0.20

+l

0.20

+m

0.18

Activations Density 0.146%

mathematical expressions and notations associated with dimensionality

No Comments

No Known Activations