INDEX

Explanations

references to food and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 munch

-0.17

ezi

-0.17

 tasty

-0.17

_recipe

-0.16

 Grocery

-0.16

 chefs

-0.15

Recipe

-0.15

 Recipes

-0.15

 kitchen

-0.15

achen

-0.15

POSITIVE LOGITS

 ques

0.22

 flank

0.21

 brisk

0.20

mac

0.20

 scrambled

0.20

las

0.20

 ribs

0.20

ice

0.19

 gyro

0.19

 Bloody

0.19

Activations Density 0.998%

references to food and dining experiences

No Comments

No Known Activations