INDEX

Explanations

connections to various brands, individuals, and 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

mazon

-0.18

Roger

-0.16

 Roger

-0.16

 Zoom

-0.15

 Gems

-0.15

oled

-0.14

eri

-0.14

 íĴį

-0.13

å®¶åºŃ

-0.13

 Glob

-0.13

POSITIVE LOGITS

undle

0.15

RVA

0.14

DFA

0.14

abase

0.14

ainers

0.14

atch

0.14

æĸĹ

0.14

anian

0.14

 Tribe

0.14

rido

0.14

Activations Density 0.013%

connections to various brands, individuals, and events

No Comments

No Known Activations