INDEX

Explanations

references to the quality of life

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oldt

-0.16

loff

-0.15

-highlight

-0.14

 Flat

-0.14

/AFP

-0.14

OLS

-0.14

Ã©f

-0.14

uming

-0.14

/Observable

-0.14

POSITIVE LOGITS

edd

0.17

 ChÃŃ

0.16

ateg

0.15

Sah

0.15

eacher

0.14

orig

0.14

sar

0.14

ì¹¨

0.13

yas

0.13

 popis

0.13

Activations Density 0.025%

references to the quality of life

No Comments

No Known Activations