INDEX

Explanations

key concepts and elements associated with significant actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

.scalablytyped

-0.21

undry

-0.17

ocy

-0.16

agens

-0.15

adu

-0.15

bakan

-0.15

á»ĥm

-0.15

abbage

-0.14

ãĥ¼ãĥ³

-0.14

åīĽ

-0.14

POSITIVE LOGITS

 PACKET

0.15

 Radical

0.14

Ø¨Ø§ÙĨ

0.14

ureau

0.14

 Abstract

0.14

ELS

0.14

 diver

0.14

 Strange

0.14

EGIN

0.14

Activations Density 0.006%

key concepts and elements associated with significant actions or events

No Comments

No Known Activations