INDEX

Explanations

features and characteristics of properties or accommodations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 cust

-0.19

 ontvangst

-0.18

 Stuff

-0.17

 Cust

-0.16

å¿½

-0.15

Stuff

-0.15

alach

-0.14

 stuffing

-0.14

ix

-0.14

-dot

-0.14

POSITIVE LOGITS

 undercover

0.21

 duct

0.20

 Federation

0.20

 entert

0.20

 entertain

0.19

alf

0.19

 internal

0.18

 Internal

0.18

 federation

0.18

 reverse

0.18

Activations Density 0.043%

features and characteristics of properties or accommodations

No Comments

No Known Activations