INDEX

Explanations

numerical information and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.19

-0.17

ugin

-0.17

ØªÙĪØ±

-0.15

ugo

-0.15

ÙĪÙĬÙĦ

-0.14

asio

-0.14

assic

-0.14

Kok

-0.14

POSITIVE LOGITS

0.28

0.27

0.19

ams

0.18

0.15

lys

0.15

tings

0.15

INGS

0.14

 Parr

0.14

Activations Density 0.049%

numerical information and dates

No Comments

No Known Activations