INDEX

Explanations

references to a specific series or topic related to films or media

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

attles

-0.17

-urlencoded

-0.16

 Oaks

-0.15

Ã¤dchen

-0.15

à¤°

-0.15

ç¿¼

-0.15

ared

-0.15

alcon

-0.14

dorf

-0.14

Zh

-0.14

POSITIVE LOGITS

imento

0.27

ements

0.25

imentos

0.24

imiento

0.22

imientos

0.22

EMENT

0.21

imenti

0.21

iment

0.20

ment

0.19

 ment

0.19

Activations Density 0.007%

references to a specific series or topic related to films or media

No Comments

No Known Activations