INDEX

Explanations

references to previous posts or writings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ovÃ©

-0.14

Ã¢

-0.14

Obr

-0.14

oler

-0.14

.setScale

-0.13

 è«

-0.13

 Edmund

-0.13

inal

-0.13

oundary

-0.13

iyas

-0.12

POSITIVE LOGITS

ãĥ³ãĥĦ

0.17

ãĥ³ãĥĨãĤ£

0.15

oksen

0.14

umu

0.14

 ÑĤÐ¾Ð¼Ñĥ

0.14

ugins

0.14

 Bash

0.13

 tang

0.13

á»ĳng

0.13

à¸Ļà¸Ļ

0.13

Activations Density 0.064%

references to previous posts or writings

No Comments

No Known Activations