INDEX

Explanations

terms related to automotive safety features and crash test results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

quals

-0.15

çĸ

-0.15

bubble

-0.15

eno

-0.14

 precision

-0.14

pit

-0.14

Eis

-0.14

Ð³Ð»

-0.14

ÙĪØªØ±

-0.13

 Cipher

-0.13

POSITIVE LOGITS

 crash

0.26

 Crash

0.24

 crashes

0.18

 safety

0.16

 Protect

0.16

 Safety

0.16

 Crush

0.16

car

0.15

 Pass

0.15

 crush

0.15

Activations Density 0.025%

terms related to automotive safety features and crash test results

No Comments

No Known Activations