INDEX

Explanations

bibliographic information and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ahr

-0.17

ahir

-0.16

à¸§

-0.15

ationally

-0.15

LR

-0.14

 Reyn

-0.13

eldon

-0.13

orge

-0.13

ine

-0.13

ohon

-0.13

POSITIVE LOGITS

 Casc

0.18

-cols

0.15

ÙĨØ§Ø¡

0.15

-pills

0.15

 Conv

0.15

mÃ¼r

0.15

Cascade

0.15

Ø²Ø©

0.14

alls

0.14

utow

0.14

Activations Density 0.583%

bibliographic information and citations

No Comments

No Known Activations