INDEX

Explanations

references to collaborative arrangements or quantities involving groups and pairs

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

ytt

-0.18

branches

-0.16

DOC

-0.15

"]=="

-0.15

Hoe

-0.15

Ã²i

-0.15

aleb

-0.14

 branches

-0.14

Ã±a

-0.14

 wedge

-0.13

POSITIVE LOGITS

.medium

0.16

 mercy

0.15

anten

0.15

pered

0.15

foil

0.14

Å¡ti

0.14

Ø·Ùĩ

0.14

ÑĢÑıÐ´

0.14

.AI

0.14

 Sist

0.14

Activations Density 0.298%

references to collaborative arrangements or quantities involving groups and pairs

No Comments

No Known Activations