INDEX

Explanations

expressions related to distances and travel times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÑĢÐ¾Ñī

-0.16

Ð¾Ð¿Ð¾Ð»

-0.16

Ø§ÙĪØ±ÛĮ

-0.15

Ø´Ø¨

-0.14

 Hizmetleri

-0.14

Forward

-0.14

 Forward

-0.14

Ð±Ð°Ñĩ

-0.13

 kÅ¯

-0.13

forward

-0.13

POSITIVE LOGITS

 drive

0.39

 away

0.32

-drive

0.31

 distant

0.28

 distance

0.28

drive

0.27

 driving

0.26

 Drive

0.25

 southwest

0.25

.drive

0.24

Activations Density 0.039%

expressions related to distances and travel times

No Comments

No Known Activations