INDEX

Explanations

references to specific car models and types

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

 Maze

-0.15

occer

-0.15

keyboard

-0.15

 Mazda

-0.15

emma

-0.14

seg

-0.14

ec

-0.14

 Honda

-0.13

Å¡ek

-0.13

æ

-0.13

POSITIVE LOGITS

omatic

0.20

 Pont

0.20

0.18

 Kaiser

0.17

 Mercury

0.17

sed

0.17

 Nash

0.17

 fins

0.16

 Rivera

0.16

 Pack

0.16

Activations Density 0.018%

references to specific car models and types

No Comments

No Known Activations