INDEX

Explanations

references to different types of food, particularly Italian dishes and their preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Witt

-0.14

 Establishment

-0.14

 puzz

-0.14

 toned

-0.14

Spl

-0.14

anne

-0.14

 spaghetti

-0.13

æ§

-0.13

onna

-0.13

spl

-0.13

POSITIVE LOGITS

 filled

0.30

filled

0.25

 filling

0.25

Filled

0.24

 stuffed

0.24

dum

0.23

 fill

0.23

 wrappers

0.23

 wrapper

0.23

 stuffing

0.23

Activations Density 0.059%

references to different types of food, particularly Italian dishes and their preparation

No Comments

No Known Activations