INDEX

Explanations

infinitive verbs indicating purpose or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

use

-0.18

çĶ¨

-0.17

Use

-0.17

 dÃ¹ng

-0.15

.use

-0.15

_use

-0.15

-use

-0.15

_USART

-0.15

atk

-0.15

 utiliser

-0.14

POSITIVE LOGITS

 help

0.24

 better

0.24

aid

0.20

 complement

0.20

better

0.19

 further

0.18

 great

0.18

 varying

0.18

 support

0.18

 supplement

0.18

Activations Density 0.221%

infinitive verbs indicating purpose or intention

No Comments

No Known Activations