INDEX

Explanations

references to links and calls to action, especially in relation to external resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ouch

-0.14

 Rogue

-0.14

 accord

-0.14

 Emerald

-0.14

asal

-0.14

ial

-0.13

è¥¿çľģ

-0.13

 Duck

-0.13

 cheap

-0.13

POSITIVE LOGITS

etta

0.18

Ð»Ð¸ÐºÐ°

0.15

obs

0.15

loub

0.15

unta

0.15

ingroup

0.14

Ã¼rk

0.13

 ÙħØ¬ÙħÙĪØ¹

0.13

flies

0.13

ETCH

0.13

Activations Density 0.083%

references to links and calls to action, especially in relation to external resources

No Comments

No Known Activations