INDEX

Explanations

technical terms and concepts related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

razier

-0.15

DTV

-0.15

oto

-0.14

 nÃ¡m

-0.13

 hang

-0.13

ag

-0.13

tha

-0.13

 rein

-0.13

.Cryptography

-0.13

#End

-0.12

POSITIVE LOGITS

/tcp

0.15

esco

0.15

foy

0.14

udget

0.14

appid

0.13

HLS

0.13

Ð°Ð½Ð¸

0.13

inks

0.13

istol

0.13

Activations Density 0.010%

technical terms and concepts related to programming and data structures

No Comments

No Known Activations