INDEX

Explanations

phrases related to duration and ongoing activities

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

 recently

-0.50

 recent

-0.46

recent

-0.42

 lately

-0.35

 Recently

-0.33

 currently

-0.32

Recently

-0.31

 Recent

-0.30

 presently

-0.29

currently

-0.28

POSITIVE LOGITS

 whenever

0.22

ä¸ĢçĽ´

0.19

 altern

0.18

avaÅŁ

0.18

 Whenever

0.17

 gradually

0.16

 repeatedly

0.15

åĲĦç§į

0.15

 nothing

0.15

 increasingly

0.15

Activations Density 0.267%

phrases related to duration and ongoing activities

No Comments

No Known Activations