INDEX

Explanations

questions that start with "Do" or "Does."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ø¨ÙĨ

-0.16

ARIO

-0.15

à¹Īà¸²à¸¢

-0.14

ATORY

-0.14

 çĻ¾

-0.14

hof

-0.14

vig

-0.13

ÑĢÐ°Ð³

-0.13

ectl

-0.13

IndexOf

-0.13

POSITIVE LOGITS

->__

0.15

rex

0.14

.utf

0.14

avis

0.14

ãģ©

0.14

 doÄŁru

0.14

 Regents

0.14

 itemprop

0.14

ressing

0.13

onth

0.13

Activations Density 0.001%

questions that start with "Do" or "Does."

No Comments

No Known Activations