INDEX

Explanations

terms associated with mathematical and computational analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ahir

-0.19

cka

-0.15

asn

-0.15

 curves

-0.15

tog

-0.14

 canv

-0.14

Curve

-0.14

ering

-0.14

obili

-0.14

à¸

-0.14

POSITIVE LOGITS

Gram

0.18

.Matrix

0.17

 Eigen

0.17

¼åĲĪ

0.17

 matrix

0.17

 eigen

0.17

 Gram

0.17

 matrices

0.16

 Trafford

0.16

eig

0.15

Activations Density 0.070%

terms associated with mathematical and computational analysis

No Comments

No Known Activations