INDEX

Explanations

patterns of repeated characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÙĨØ´

-0.15

zend

-0.15

Ð½ÐµÐ·

-0.14

atoi

-0.14

ENE

-0.14

orr

-0.14

anking

-0.13

ÐºÐ»Ð°Ð´

-0.13

ated

-0.13

oric

-0.13

POSITIVE LOGITS

aterangepicker

0.17

urette

0.15

aurus

0.15

embre

0.15

 ApplicationException

0.14

ilir

0.14

åľĴ

0.14

InnerText

0.14

ADV

0.14

_ALIAS

0.14

Activations Density 0.002%

patterns of repeated characters or symbols

No Comments

No Known Activations