INDEX

Explanations

phrases related to automotive repair and modification

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

plusplus

-0.15

æĹĹ

-0.14

achat

-0.14

ocio

-0.14

 suck

-0.14

 Stanley

-0.14

_MS

-0.13

 mechan

-0.13

adesh

-0.13

xAA

-0.13

POSITIVE LOGITS

 frame

0.25

 khung

0.24

 chassis

0.24

frame

0.23

 Frame

0.21

 Wish

0.21

	frame

0.20

tub

0.20

éª¨

0.20

 firewall

0.20

Activations Density 0.071%

phrases related to automotive repair and modification

No Known Activations