INDEX

Explanations

references to media organizations and business entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 ?><?

-0.15

ÑıÐ³

-0.14

pec

-0.14

 Predator

-0.14

Thu

-0.14

/os

-0.14

prene

-0.14

_Reference

-0.13

Ð¾ÑģÑĮ

-0.13

ë©ĺ

-0.13

POSITIVE LOGITS

-owned

0.18

trx

0.16

 Ø§ÙĦÙħÙĨØª

0.15

trys

0.14

Ð¸ÑĤÐ¸

0.14

æĹĹ

0.14

ÑĸÐ»Ð°

0.14

kova

0.13

bolt

0.13

ÙħØª

0.13

Activations Density 0.151%

references to media organizations and business entities

No Comments

No Known Activations