INDEX

Explanations

features related to automotive technology and safety systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

¥¤

-0.18

-0.14

æ¯

-0.14

PSU

-0.14

 slee

-0.14

phem

-0.14

à¥Ĥà¤¤

-0.13

ipt

-0.13

onda

-0.13

POSITIVE LOGITS

 Collision

0.23

 warnings

0.23

 collision

0.22

 warning

0.21

 lane

0.21

 Assist

0.20

 assistance

0.20

 Rear

0.20

 assist

0.20

 Lane

0.19

Activations Density 0.010%

features related to automotive technology and safety systems

No Comments

No Known Activations