INDEX

Explanations

phrases related to vehicle features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

umas

-0.15

assium

-0.15

imon

-0.15

å¯¿

-0.14

aupt

-0.14

eldig

-0.14

iras

-0.14

.Metro

-0.14

Ħĸ

-0.14

 Affero

-0.13

POSITIVE LOGITS

 exterior

0.23

 safety

0.23

 cabin

0.22

 Safety

0.21

 interior

0.21

 driver

0.20

 Exterior

0.20

 Driver

0.20

 hatch

0.18

cab

0.18

Activations Density 0.040%

phrases related to vehicle features

No Comments

No Known Activations