INDEX

Explanations

references to coding and programming terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

utm

-0.16

agit

-0.15

OLID

-0.15

acci

-0.14

ilia

-0.14

 Fluent

-0.14

enko

-0.13

aniel

-0.13

ault

-0.13

etler

-0.13

POSITIVE LOGITS

 import

0.49

import

0.38

 from

0.37

 importing

0.33

 imports

0.33

	import

0.33

 Import

0.32

/import

0.30

from

0.30

-import

0.29

Activations Density 0.007%

references to coding and programming terminology

No Comments

No Known Activations