INDEX

Explanations

punctuation marks and their frequency in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

als

-0.15

ery

-0.15

icone

-0.14

_fwd

-0.14

 corner

-0.14

esson

-0.14

[:]

-0.14

apiKey

-0.14

-0.13

iele

-0.13

POSITIVE LOGITS

 https

0.23

vak

0.17

https

0.17

 Creative

0.17

untu

0.16

ä¸¸

0.15

iores

0.15

ÏĢÎ¿ÏĦÎµ

0.15

 âĨĲ

0.15

 http

0.15

Activations Density 0.064%

punctuation marks and their frequency in text

No Comments

No Known Activations