INDEX

Explanations

instances of the word "climb" and its variations, as well as related actions involving ascending

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

alley

-0.17

ebo

-0.16

jerne

-0.16

arme

-0.15

 dips

-0.15

éľĩ

-0.14

å»ºè¨Ń

-0.14

ozem

-0.14

plevel

-0.14

 ConfigureServices

-0.14

POSITIVE LOGITS

Kil

0.26

 stairs

0.24

Mt

0.24

 Mount

0.23

 walls

0.21

kil

0.21

 Jacobs

0.21

Mt

0.19

 trees

0.18

 aboard

0.18

Activations Density 0.039%

instances of the word "climb" and its variations, as well as related actions involving ascending

No Comments

No Known Activations