INDEX

Explanations

references to specific book titles and their series

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

roscope

-0.16

pole

-0.16

 bound

-0.16

 mass

-0.15

 Pole

-0.14

/tos

-0.14

 pole

-0.14

Tol

-0.14

 Sans

-0.14

POSITIVE LOGITS

aday

0.15

gfx

0.15

 ÎºÏį

0.14

tik

0.14

ÐµÑĢÐ¸Ð½

0.14

 Rubio

0.14

arov

0.14

ë²¨

0.14

oppins

0.14

adic

0.14

Activations Density 0.013%

references to specific book titles and their series

No Comments

No Known Activations