INDEX

Explanations

specific instructions or details related to actions and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

áº¥y

-0.15

 Kinder

-0.15

audi

-0.14

 Ø¯Ùħ

-0.14

.UnitTesting

-0.14

frauen

-0.14

xeb

-0.14

Ú¯Ùĩ

-0.14

olet

-0.13

 kvinder

-0.13

POSITIVE LOGITS

0.17

apan

0.16

UA

0.15

 ç´

0.15

riers

0.15

0.14

 Powder

0.14

idos

0.14

 lantern

0.14

ateg

0.14

Activations Density 0.037%

specific instructions or details related to actions and processes

No Comments

No Known Activations