INDEX

Explanations

details related to cars and automotive experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.scalablytyped

-0.15

ManagerInterface

-0.15

 bund

-0.15

ittest

-0.15

readcr

-0.14

erdem

-0.14

Ð¾Ð´Ð¾

-0.14

.UTF

-0.14

ç¬

-0.14

ctl

-0.14

POSITIVE LOGITS

 resto

0.20

 donor

0.20

 Custom

0.18

 restoration

0.18

 complete

0.18

 custom

0.18

Custom

0.16

complete

0.16

 Craigslist

0.16

Activations Density 0.057%

details related to cars and automotive experiences

No Comments

No Known Activations