INDEX

Explanations

references to parameters or documentation terminology in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

wayne

-0.16

erten

-0.16

ÑıÑĩ

-0.15

 Pence

-0.14

 nhau

-0.14

ä¹ĭ

-0.14

 Prelude

-0.14

aida

-0.14

cede

-0.14

 lets

-0.13

POSITIVE LOGITS

param

0.48

 param

0.38

-param

0.30

 Param

0.29

Param

0.29

return

0.28

.param

0.28

	param

0.27

throws

0.26

_param

0.26

Activations Density 0.005%

references to parameters or documentation terminology in coding contexts

No Comments

No Known Activations