INDEX

Explanations

technical terminology related to programming and data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 patriotism

-0.16

 Pandora

-0.16

 pornography

-0.16

 prefixed

-0.15

erras

-0.15

 Pentagon

-0.15

 Pearce

-0.15

Pap

-0.15

ela

-0.15

rove

-0.15

POSITIVE LOGITS

 post

1.09

post

0.99

 Post

0.94

-post

0.92

Post

0.91

_post

0.85

.post

0.84

 Ð¿Ð¾ÑģÑĤ

0.75

	post

0.75

_Post

0.71

Activations Density 0.240%

technical terminology related to programming and data management

No Comments

No Known Activations