INDEX

Explanations

references to various computational tools and parameters in data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Randall

-0.14

pst

-0.14

ëłĪ

-0.14

ivant

-0.14

 jsonData

-0.13

Ð±ÑĥÐ´ÑĮ

-0.13

 Superv

-0.13

ystate

-0.13

PTS

-0.13

ivol

-0.13

POSITIVE LOGITS

ãĥĬãĥ«

0.18

uros

0.15

_mpi

0.15

 à¸¿

0.15

Ã¤ft

0.15

ug

0.14

uss

0.14

inion

0.14

ance

0.14

 yaÅŁ

0.13

Activations Density 0.023%

references to various computational tools and parameters in data processing

No Comments

No Known Activations