INDEX

Explanations

terms and phrases related to blindness and accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Observer

-0.16

 observer

-0.15

 Observer

-0.15

 observed

-0.15

ertz

-0.15

nick

-0.15

/embed

-0.15

 arch

-0.14

arsers

-0.14

anlÄ±

-0.13

POSITIVE LOGITS

 blind

0.31

 blindness

0.28

 Blind

0.28

blind

0.28

-blind

0.24

 blinds

0.21

 blinded

0.20

çĽ

0.18

/bl

0.18

Br

0.18

Activations Density 0.022%

terms and phrases related to blindness and accessibility

No Comments

No Known Activations