INDEX

Explanations

mentions of the name "Mario" and related content in various contexts

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

ner

-0.17

ncy

-0.16

RTOS

-0.15

 Assembly

-0.15

aju

-0.15

ifecycle

-0.14

-urlencoded

-0.14

ppo

-0.14

umer

-0.14

naire

-0.14

POSITIVE LOGITS

iac

0.17

illac

0.17

lene

0.17

elle

0.16

oler

0.15

yal

0.15

encion

0.15

kest

0.15

_VOID

0.14

avit

0.14

Activations Density 0.008%

mentions of the name "Mario" and related content in various contexts

No Comments

No Known Activations