INDEX

Explanations

content related to analysis and summaries of information, specifically in the context of discussions or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Hood

-0.15

allo

-0.14

 Crud

-0.14

_HI

-0.14

rike

-0.14

elling

-0.14

ellipsis

-0.13

subtype

-0.13

eriod

-0.13

Curso

-0.13

POSITIVE LOGITS

 links

0.29

 information

0.26

 lists

0.23

 list

0.23

 details

0.23

 info

0.22

 tips

0.20

links

0.20

 Links

0.19

 description

0.19

Activations Density 0.358%

content related to analysis and summaries of information, specifically in the context of discussions or updates

No Comments

No Known Activations