INDEX

Explanations

numerical data related to measurements and specifications

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

Deg

-0.17

opr

-0.15

ziej

-0.15

pios

-0.15

Deg

-0.15

years

-0.14

/Table

-0.14

ams

-0.14

Æ°

-0.14

/AFP

-0.14

POSITIVE LOGITS

 kilomet

0.21

mil

0.21

km

0.20

ÃĹ

0.20

 meter

0.19

 minut

0.19

–

0.18

kil

0.18

âĢ°

0.18

 quil

0.17

Activations Density 0.020%

numerical data related to measurements and specifications

No Comments

No Known Activations