INDEX

Explanations

phrases indicating the importance of roles or contributions 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 @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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§ÙĦØ«

-0.16

ikel

-0.14

arta

-0.14

latable

-0.14

 giá»Ŀ

-0.14

æĮģãģ¡

-0.14

session

-0.13

ruh

-0.13

oto

-0.13

ustos

-0.13

POSITIVE LOGITS

ustr

0.15

platz

0.14

issen

0.14

asso

0.14

idge

0.14

andes

0.13

cen

0.13

ÑģÑĤÐ°Ð²

0.13

Activations Density 0.020%

phrases indicating the importance of roles or contributions in various contexts

No Comments

No Known Activations