INDEX

Explanations

expressions of confusion or requests for help

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

enia

-0.15

 ActionTypes

-0.14

angu

-0.14

umo

-0.14

ikip

-0.14

sell

-0.14

 Congratulations

-0.13

stav

-0.13

ese

-0.13

POSITIVE LOGITS

 help

0.25

 assistance

0.23

 Help

0.23

 Hilfe

0.21

-help

0.21

 HELP

0.20

 Assistance

0.20

Help

0.19

 appreciated

0.19

 appreciate

0.19

Activations Density 0.066%

expressions of confusion or requests for help

No Comments

No Known Activations