INDEX

Explanations

specific references to recipes and cooking-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 cooked

-0.20

cooked

-0.18

ÑĢÐ°Ð²Ð°

-0.17

Ø±Ùħ

-0.15

ilton

-0.15

emez

-0.15

hausen

-0.15

 Lions

-0.15

 submenu

-0.15

chter

-0.14

POSITIVE LOGITS

Lid

0.19

ATK

0.18

 seri

0.17

 Emer

0.17

 Bare

0.17

 Serious

0.17

 åŃ

0.16

.ep

0.15

 Comfort

0.15

 Clarkson

0.15

Activations Density 0.065%

specific references to recipes and cooking-related content

No Comments

No Known Activations