INDEX

Explanations

technical terms and jargon related to software and engineering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

_lite

-0.20

ingle

-0.17

emouth

-0.16

dden

-0.16

asal

-0.16

ToOne

-0.15

icense

-0.15

utomation

-0.15

defgroup

-0.14

quential

-0.14

POSITIVE LOGITS

lesh

0.16

el

0.14

Äįi

0.14

uyo

0.14

yo

0.14

ing

0.14

oki

0.14

.BorderFactory

0.14

hos

0.14

 Rica

0.13

Activations Density 0.003%

technical terms and jargon related to software and engineering

No Comments

No Known Activations