INDEX

Explanations

references to numerical data and statistics

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

anca

-0.15

iges

-0.15

*>*

-0.15

processable

-0.14

_simps

-0.14

ollow

-0.14

otto

-0.14

_ASYNC

-0.14

grams

-0.13

mony

-0.13

POSITIVE LOGITS

/Dk

0.15

teg

0.14

unto

0.14

-opacity

0.14

ahoo

0.14

 centr

0.14

íĩ´

0.14

ERSHEY

0.14

tbl

0.14

udson

0.14

Activations Density 0.006%

references to numerical data and statistics

No Comments

No Known Activations