INDEX

Explanations

phrases related to the structure and organization of a document or paper

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

kinson

-0.18

ral

-0.17

ubble

-0.16

jin

-0.16

Ð³Ð¸

-0.15

è¾

-0.14

uster

-0.14

 Ð¿ÑĢÐ¸Ð·

-0.14

 Drawer

-0.14

ux

-0.14

POSITIVE LOGITS

rypton

0.17

inton

0.15

nonnull

0.14

BOOT

0.14

ennen

0.14

AccessType

0.14

.byte

0.14

andest

0.14

odash

0.14

antry

0.14

Activations Density 0.010%

phrases related to the structure and organization of a document or paper

No Comments

No Known Activations