INDEX

Explanations

comparative phrases that highlight differences or superiority

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

oux

-0.15

çª

-0.14

icia

-0.14

æĹ¢

-0.14

 HWND

-0.13

esktop

-0.13

å¢

-0.13

mu

-0.13

ocene

-0.13

Ð²Ð°Ð¹

-0.13

POSITIVE LOGITS

à¸²à¸ĺ

0.20

lage

0.15

elerik

0.15

ori

0.14

íĥĦ

0.14

uff

0.14

Äħd

0.14

ibar

0.14

oÅĻ

0.13

igm

0.13

Activations Density 0.053%

comparative phrases that highlight differences or superiority

No Comments

No Known Activations