INDEX

Explanations

titles and honors associated with knights and distinguished individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

otas

-0.16

ERGE

-0.15

otor

-0.15

adolu

-0.15

oon

-0.14

ollar

-0.14

ters

-0.14

ãĥ¼ãĤ¯

-0.14

 nÄĥ

-0.14

 rare

-0.14

POSITIVE LOGITS

ships

0.24

ship

0.23

0.15

ified

0.15

rett

0.15

SHIP

0.14

inned

0.14

orable

0.14

Ã¼h

0.14

modulo

0.14

Activations Density 0.046%

titles and honors associated with knights and distinguished individuals

No Comments

No Known Activations