INDEX

Explanations

instances of occurrences or expectations of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

tracted

-0.15

cio

-0.14

trieve

-0.14

æ¥½ãģĹ

-0.14

ä¸ĬãģĴ

-0.14

ICON

-0.13

 mote

-0.13

 mint

-0.13

ptions

-0.13

POSITIVE LOGITS

 hear

0.26

 hearing

0.24

 hears

0.20

 finally

0.19

see

0.19

hear

0.19

 know

0.18

 Hear

0.18

 watch

0.18

 think

0.17

Activations Density 0.079%

instances of occurrences or expectations of actions

No Comments

No Known Activations