INDEX

Explanations

specific details about vehicles and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

çĵľ

-0.15

mot

-0.15

 Dragons

-0.14

DBG

-0.14

 Goods

-0.14

ivar

-0.14

sted

-0.14

 motor

-0.13

ines

-0.13

igne

-0.13

POSITIVE LOGITS

 Pont

0.29

Pri

0.27

Bu

0.26

 Accord

0.25

 Civic

0.25

 Saturn

0.25

Inf

0.25

Pont

0.24

 Explorer

0.24

 Sonata

0.22

Activations Density 0.106%

specific details about vehicles and their characteristics

No Comments

No Known Activations