INDEX

Explanations

complex or nuanced concepts and relationships

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

BITS

-0.15

laden

-0.15

opoulos

-0.14

ancial

-0.14

$MESS

-0.14

arken

-0.14

–

-0.13

ieces

-0.13

frica

-0.13

ika

-0.13

POSITIVE LOGITS

artner

0.14

InstanceOf

0.14

à¥įà¤¤à¤µ

0.13

Ø§ÙħÙĬ

0.13

olute

0.13

ephy

0.13

ackbar

0.13

croft

0.13

vang

0.12

Activations Density 0.420%

complex or nuanced concepts and relationships

No Comments

No Known Activations