INDEX

Explanations

references to software versions and security vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

allis

-0.18

Ã¼lt

-0.17

zh

-0.16

 Rhodes

-0.15

quez

-0.14

RH

-0.14

fon

-0.14

ÅĦ

-0.14

mb

-0.14

itom

-0.14

POSITIVE LOGITS

exo

0.17

/Dk

0.16

urum

0.15

.gwt

0.15

ereum

0.14

áº¹n

0.14

smith

0.14

anza

0.14

 Spinner

0.14

anger

0.14

Activations Density 0.084%

references to software versions and security vulnerabilities

No Comments

No Known Activations