INDEX

Explanations

phrases that describe conditions or properties applicable to all elements in a set or context

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

ekim

-0.16

catid

-0.16

zek

-0.15

reative

-0.15

Ø§Ø¨Ø¹

-0.14

stem

-0.14

geÃ§

-0.14

iyel

-0.14

TI

-0.13

Ix

-0.13

POSITIVE LOGITS

0.15

jun

0.14

dol

0.14

 ÑģÐµÐ±Ðµ

0.14

itia

0.14

gor

0.14

 khÃŃ

0.14

0.13

illard

0.13

Activations Density 0.040%

phrases that describe conditions or properties applicable to all elements in a set or context

No Comments

No Known Activations