INDEX

Explanations

frequency-related terminology and measurements

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

 Spicer

-0.17

haps

-0.15

coffee

-0.14

 Ragnar

-0.14

'..

-0.14

 wedge

-0.14

 Ø§ÙĦØ£ÙħØ±

-0.14

ç¡

-0.14

Sampler

-0.14

.addHandler

-0.13

POSITIVE LOGITS

 Bird

0.19

 bird

0.18

 Young

0.17

 Cash

0.17

YM

0.17

 Tune

0.17

 Wayne

0.16

 behind

0.16

yme

0.16

 Trinidad

0.15

Activations Density 0.003%

frequency-related terminology and measurements

No Comments

No Known Activations