INDEX

Explanations

mathematical notations and expressions related to limits and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-urlencoded

-0.15

omap

-0.14

 âĨĴ↵↵

-0.14

æ³Ĭ

-0.14

ebb

-0.14

kening

-0.13

marsh

-0.13

tir

-0.13

ania

-0.13

 Scarborough

-0.13

POSITIVE LOGITS

hoo

0.14

 Mage

0.14

 Downs

0.14

LRV

0.14

ristol

0.13

 solids

0.13

ource

0.13

dry

0.13

 depressed

0.13

Ð°Ð¹ÑĤ

0.13

Activations Density 0.109%

mathematical notations and expressions related to limits and conditions

No Comments

No Known Activations