INDEX

Explanations

instances of the special character used in various contexts, suggesting an interest in emphasis or specific formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

—

-0.16

bbc

-0.14

ernel

-0.14

 âĢķ

-0.14

ccp

-0.14

licence

-0.14

.gdx

-0.14

/inet

-0.14

Ã¡ce

-0.14

 presidents

-0.13

POSITIVE LOGITS

 Beth

0.30

Hob

0.30

MS

0.28

Beth

0.27

MS

0.25

 Mason

0.25

MF

0.25

 Council

0.24

Council

0.23

eth

0.22

Activations Density 0.005%

instances of the special character used in various contexts, suggesting an interest in emphasis or specific formatting

No Comments

No Known Activations