INDEX

Explanations

punctuation and numerical values or patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ustom

-0.15

secutive

-0.14

wner

-0.14

ÑĥÐ»Ð¸

-0.14

ipher

-0.14

tha

-0.14

orex

-0.13

)âĢı

-0.13

.Begin

-0.13

SYNC

-0.13

POSITIVE LOGITS

Correction

0.22

 tags

0.19

 Meanwhile

0.18

Meanwhile

0.18

COR

0.18

 Else

0.17

 Copyright

0.16

 overall

0.16

anela

0.16

 follow

0.16

Activations Density 0.086%

punctuation and numerical values or patterns

No Comments

No Known Activations