INDEX

Explanations

expressions related to food enjoyment and culinary experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

odyn

-0.15

ourn

-0.15

UNT

-0.14

Ã§on

-0.14

Ã³r

-0.14

akeup

-0.14

Ð¼ÐµÑĤÑĮ

-0.14

eger

-0.13

exas

-0.13

ogo

-0.13

POSITIVE LOGITS

 addictive

0.22

dro

0.19

swo

0.18

_hook

0.17

 speech

0.17

 converted

0.16

 blown

0.16

 addicted

0.16

gas

0.16

GAS

0.16

Activations Density 0.169%

expressions related to food enjoyment and culinary experiences

No Comments

No Known Activations