INDEX

Explanations

references to individuals associated with memorials or tributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

noch

-0.15

Ã¢l

-0.14

PCA

-0.14

inel

-0.13

agoon

-0.13

ogl

-0.13

Ø¬Ø§ÙĨ

-0.13

 Steph

-0.13

ending

-0.12

POSITIVE LOGITS

please

0.28

 please

0.28

ple

0.28

 Please

0.23

Please

0.23

Ple

0.22

è¯·

0.21

ï¼Įè¯·

0.21

 bitte

0.21

è«ĭ

0.20

Activations Density 0.040%

references to individuals associated with memorials or tributes

No Comments

No Known Activations