INDEX

Explanations

ellipses or representations of uncertainty

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ing

-0.18

Ø§

-0.17

ed

-0.16

entifier

-0.16

lings

-0.15

edb

-0.15

aries

-0.15

ancybox

-0.15

gary

-0.15

abyrinth

-0.14

POSITIVE LOGITS

0.24

Ùĩ

0.22

0.19

 "...

0.17

orz

0.17

à¤¨

0.16

rÃ¥

0.16

ska

0.16

sure

0.16

sik

0.15

Activations Density 0.056%

ellipses or representations of uncertainty

No Known Activations