INDEX

Explanations

references to specific plans or proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.gdx

-0.18

peq

-0.16

gang

-0.16

Ø®Ø§ÙĨÙĩ

-0.15

anse

-0.15

clamation

-0.15

/******/

-0.15

maal

-0.15

ipa

-0.14

POSITIVE LOGITS

etary

0.31

isphere

0.26

ter

0.22

terior

0.22

 Parenthood

0.21

egg

0.19

-ahead

0.17

illas

0.17

ificacion

0.17

cke

0.16

Activations Density 0.052%

references to specific plans or proposals

No Comments

No Known Activations