INDEX

Explanations

mentions of professional organizations and associations

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

 tÃ½

-0.17

cent

-0.15

 notoriously

-0.14

@student

-0.14

semblies

-0.13

otify

-0.13

")));

-0.13

 porad

-0.13

ettings

-0.13

 strugg

-0.13

POSITIVE LOGITS

to

0.28

 ready

0.26

 finally

0.20

 looking

0.20

 poised

0.20

 headed

0.19

 heading

0.19

 still

0.18

bol

0.18

Activations Density 0.283%

mentions of professional organizations and associations

No Comments

No Known Activations