INDEX

Explanations

punctuation marks and their associated usage in the text

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

á»ī

-0.18

iteli

-0.18

eless

-0.16

castle

-0.15

_ASM

-0.15

 meiden

-0.14

uncia

-0.14

getReference

-0.14

ogne

-0.14

forgettable

-0.14

POSITIVE LOGITS

0.16

ag

0.16

ãĥ©ãĥ¼

0.15

zo

0.15

 Rash

0.14

organic

0.14

ns

0.14

ÙħØ§Ùħ

0.13

Mal

0.13

Activations Density 0.449%

punctuation marks and their associated usage in the text

No Comments

No Known Activations