INDEX

Explanations

terms related to suspension or pauses in activities or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

æ¸Ī

-0.16

erc

-0.15

azzo

-0.14

ivas

-0.14

nom

-0.14

æł·çļĦ

-0.14

yz

-0.14

views

-0.13

 Hurt

-0.13

ÑĩÐ¸ÐºÐ°

-0.13

POSITIVE LOGITS

 susp

0.25

 suspend

0.24

 suspended

0.23

pending

0.22

 suspension

0.22

suspend

0.21

 Susp

0.20

icious

0.20

 disbelief

0.20

Susp

0.20

Activations Density 0.023%

terms related to suspension or pauses in activities or services

No Comments

No Known Activations