INDEX

Explanations

discussions about agreements and terms of employment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

antt

-0.15

alette

-0.15

Ø§ÙĪØ±

-0.15

InitStruct

-0.15

åĵ²

-0.14

Ð¾Ð»Ð½Ð¸ÑĤÐµÐ»ÑĮ

-0.14

braco

-0.14

æĨ

-0.14

.PERMISSION

-0.13

ntax

-0.13

POSITIVE LOGITS

 \↵

0.17

 Ð²ÐºÑĥ

0.15

co

0.15

AFX

0.14

 Paula

0.14

TBD

0.14

 Abed

0.13

Activations Density 1.038%

discussions about agreements and terms of employment

No Comments

No Known Activations