INDEX

Explanations

formatting or structural elements in documents, particularly those related to articles or records

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ÑĳÑĤ

-0.16

gre

-0.14

 refr

-0.14

amba

-0.14

Unc

-0.14

 è¦

-0.14

edeki

-0.14

letic

-0.14

oda

-0.14

kb

-0.13

POSITIVE LOGITS

ModelProperty

0.15

Hir

0.15

MimeType

0.14

 Hancock

0.14

 Flood

0.14

èģ

0.14

obot

0.14

ë°©

0.14

vi

0.13

á»©

0.13

Activations Density 0.002%

formatting or structural elements in documents, particularly those related to articles or records

No Comments

No Known Activations