INDEX

Explanations

descriptions and actions related to food preparation and ingredients

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 portfolio

-0.16

portfolio

-0.16

ana

-0.16

ovel

-0.15

dol

-0.15

isser

-0.15

esa

-0.14

rav

-0.14

 braz

-0.14

ichen

-0.14

POSITIVE LOGITS

hus

0.27

 skins

0.26

èĴĤ

0.26

 hull

0.25

Hus

0.23

discard

0.23

 Skin

0.23

 skin

0.22

 discard

0.22

 stems

0.22

Activations Density 0.042%

descriptions and actions related to food preparation and ingredients

No Comments

No Known Activations