INDEX

Explanations

references to transportation methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uka

-0.17

anova

-0.16

 upstream

-0.16

 BorderRadius

-0.15

Ä°R

-0.15

marvin

-0.15

 downstream

-0.15

Æ¡i

-0.14

dge

-0.14

 invo

-0.14

POSITIVE LOGITS

 line

0.18

 Barr

0.18

 Line

0.16

izontal

0.15

elines

0.14

 Mastery

0.14

 lines

0.14

istogram

0.14

olik

0.13

 barr

0.13

Activations Density 0.039%

references to transportation methods

No Comments

No Known Activations