INDEX

Explanations

references to academic papers and their structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

riors

-0.16

stakes

-0.16

rior

-0.15

 hide

-0.15

 Economy

-0.15

ellar

-0.15

ior

-0.15

 degree

-0.14

add

-0.14

Ã¤ter

-0.14

POSITIVE LOGITS

GestureRecognizer

0.14

 ÄĳÃ¡ng

0.14

 awakeFromNib

0.14

egov

0.13

 ÑĥÑģÑĤÑĢÐ¾Ð¹ÑģÑĤÐ²Ð°

0.13

_mD

0.13

 ÑĥÑģÑĤÑĢÐ¾Ð¹

0.13

[::-

0.13

.gwt

0.13

 Horton

0.13

Activations Density 0.214%

references to academic papers and their structure

No Comments

No Known Activations