INDEX

Explanations

statements or questions expressing uncertainty or lack of knowledge

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

Not in Any Lists

No Comments

Negative Logits

yc

-0.15

 Ð²Ð¾ÑĤ

-0.14

asley

-0.14

bla

-0.14

chod

-0.13

ASTE

-0.13

asu

-0.13

oucher

-0.13

dration

-0.13

Ð¾Ð»Ð¾Ð¶

-0.13

POSITIVE LOGITS

 whether

0.27

why

0.27

how

0.24

whether

0.23

how

0.20

why

0.20

 Whether

0.19

 exactly

0.18

Whether

0.17

æĺ¯åĲ¦

0.17

Activations Density 0.048%

statements or questions expressing uncertainty or lack of knowledge

No Comments

No Known Activations