INDEX

Explanations

expressions of boasting or bragging about achievements or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

arkin

-0.18

wie

-0.16

eti

-0.15

pData

-0.15

apsed

-0.15

 Colomb

-0.15

aise

-0.14

unicode

-0.14

 Laws

-0.14

 Pearson

-0.14

POSITIVE LOGITS

engu

0.16

ÑĩÐ¸

0.15

ably

0.14

Builders

0.14

.ci

0.14

à¥Ĥà¤¦

0.14

ØºÙĨ

0.14

afari

0.14

nest

0.13

itia

0.13

Activations Density 0.009%

expressions of boasting or bragging about achievements or qualities

No Comments

No Known Activations