INDEX

Explanations

programming symbols and operators related to memory management or object referencing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

utter

-0.16

ãĥ¼ãĥ

-0.16

dit

-0.15

ais

-0.15

esti

-0.15

ObjectType

-0.14

go

-0.14

NewItem

-0.14

dens

-0.14

assi

-0.14

POSITIVE LOGITS

nbsp

0.17

oplayer

0.15

amp

0.15

hra

0.14

emsp

0.14

 Barth

0.13

 McInt

0.13

rodu

0.13

BootApplication

0.13

illard

0.13

Activations Density 0.001%

programming symbols and operators related to memory management or object referencing

No Comments

No Known Activations