INDEX

Explanations

references to historical documents and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

afia

-0.17

Ã³ng

-0.15

iales

-0.15

umo

-0.14

:^

-0.14

onse

-0.14

Mocks

-0.14

Ø§ÙĪÙĬØ©

-0.14

acionales

-0.14

iaÅĤa

-0.14

POSITIVE LOGITS

erve

0.17

Ð»Ð°Ñĩ

0.14

otten

0.14

former

0.14

ADC

0.14

st

0.13

README

0.13

æĵ¦

0.13

osten

0.13

iel

0.13

Activations Density 0.143%

references to historical documents and literary works

No Comments

No Known Activations