INDEX

Explanations

instances of recognition or reaction to events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

platz

-0.16

agram

-0.15

ãĤĪãģŃ

-0.14

 combust

-0.14

azon

-0.14

.named

-0.14

aid

-0.13

ulings

-0.13

 tongue

-0.13

POSITIVE LOGITS

 applause

0.20

 much

0.17

 audience

0.17

oha

0.15

 cheers

0.15

 laughter

0.15

IMS

0.14

urat

0.14

 crowd

0.14

uco

0.14

Activations Density 0.119%

instances of recognition or reaction to events or experiences

No Comments

No Known Activations