INDEX

Explanations

questions and critiques regarding dining habits and social norms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 staging

-0.16

imeo

-0.15

Non

-0.15

elop

-0.15

Non

-0.14

#ad

-0.14

 overrun

-0.14

pls

-0.14

_non

-0.14

ĶåĽŀ

-0.14

POSITIVE LOGITS

rut

0.15

idian

0.15

ÑİÑĢ

0.15

çľģ

0.14

.Lib

0.14

asic

0.14

rud

0.14

ãĤ¹ãĤ¯

0.14

ruta

0.14

ÑĪÐ¸Ð½

0.14

Activations Density 0.114%

questions and critiques regarding dining habits and social norms

No Comments

No Known Activations