INDEX

Explanations

references to safety features and performance in vehicles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ovit

-0.16

entiful

-0.16

.lu

-0.15

/browse

-0.15

 McMahon

-0.15

 Manning

-0.14

é¼

-0.14

weg

-0.14

arta

-0.14

Ð¾Ð³Ð¾Ð´

-0.13

POSITIVE LOGITS

BS

0.23

 Hero

0.21

Mah

0.19

 Alto

0.18

Hero

0.18

Inn

0.18

Variant

0.17

hero

0.17

Mar

0.17

 exports

0.17

Activations Density 0.029%

references to safety features and performance in vehicles

No Comments

No Known Activations