INDEX

Explanations

specifications and details related to vehicle components and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 Tone

-0.15

cki

-0.15

bow

-0.15

 Tale

-0.15

æ¸

-0.14

ertino

-0.14

rawer

-0.14

vox

-0.14

usu

-0.14

itioner

-0.14

POSITIVE LOGITS

 tire

0.45

 tires

0.42

 tread

0.40

 rubber

0.37

 tyre

0.36

 tyres

0.34

 Tire

0.34

 Rubber

0.32

 Mich

0.29

vul

0.27

Activations Density 0.039%

specifications and details related to vehicle components and performance

No Comments

No Known Activations