INDEX

Explanations

discussions about car specifications and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

akis

-0.14

ÑģÐ°Ð¼

-0.14

æĳ©

-0.14

 æİ¨

-0.13

vil

-0.13

Rep

-0.13

casecmp

-0.13

 Lois

-0.13

Gef

-0.13

POSITIVE LOGITS

 rear

0.21

Cargo

0.19

 Cargo

0.18

 cargo

0.17

 hatch

0.17

 diagram

0.16

addock

0.16

 Payload

0.16

van

0.15

ecial

0.15

Activations Density 0.033%

discussions about car specifications and features

No Comments

No Known Activations