INDEX

Explanations

punctuation marks and their usage within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

CHANT

-0.15

indre

-0.15

ourg

-0.13

Ø±ÛĮÙĤ

-0.13

ÏĥÎ¹Î±

-0.13

acb

-0.12

.hd

-0.12

clid

-0.12

Ĵáŀ

-0.12

oucher

-0.12

POSITIVE LOGITS

/or

0.24

ients

0.23

/OR

0.19

ifice

0.17

chter

0.16

atre

0.16

/-

0.16

/etc

0.16

raquo

0.15

nbsp

0.15

Activations Density 0.077%

punctuation marks and their usage within text

No Comments

No Known Activations