INDEX

Explanations

components related to a software framework or application architecture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

alah

-0.15

 Nack

-0.15

legg

-0.15

rient

-0.14

annon

-0.14

ongan

-0.14

éĴ®

-0.14

meric

-0.14

uchi

-0.14

levant

-0.13

POSITIVE LOGITS

\M

0.25

0.24

::

0.21

\V

0.17

\C

0.17

Bundle

0.17

\F

0.17

\D

0.16

\E

0.16

0.15

Activations Density 0.049%

components related to a software framework or application architecture

No Comments

No Known Activations