INDEX

Explanations

references to social media platforms and audience engagement actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oso

-0.17

venues

-0.15

Ð¾ÑĤÑĥ

-0.15

hood

-0.14

pong

-0.14

ney

-0.14

neys

-0.14

è¹

-0.14

lier

-0.14

indo

-0.13

POSITIVE LOGITS

AGER

0.16

ëĭĿ

0.15

 mort

0.14

anium

0.14

noinspection

0.14

Lux

0.14

 referenced

0.13

 Scar

0.13

 NUITKA

0.13

Activations Density 0.139%

references to social media platforms and audience engagement actions

No Comments

No Known Activations