INDEX

Explanations

mentions of specific locations or residences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

mont

-0.15

mal

-0.15

igin

-0.14

vit

-0.14

Ã¢u

-0.14

Ø«Ø§ÙĦ

-0.13

 gall

-0.13

ÑĤÐ¸Ð½

-0.13

çĭ

-0.13

 Tank

-0.13

POSITIVE LOGITS

chu

0.17

ayette

0.15

 mimeType

0.14

ardo

0.14

 ApiController

0.13

GGLE

0.13

PickerController

0.13

iliz

0.13

ÙĪÙģ

0.13

Ã©ment

0.13

Activations Density 0.044%

mentions of specific locations or residences

No Comments

No Known Activations