INDEX

Explanations

aspects related to the addition of new features or components in a technical context

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

alsy

-0.16

agram

-0.15

parator

-0.15

odos

-0.15

phia

-0.14

Jub

-0.14

ilst

-0.14

gili

-0.14

ansk

-0.14

ÑģÐºÐ¾Ð¼

-0.14

POSITIVE LOGITS

 onto

0.46

onto

0.39

 into

0.33

into

0.27

Ont

0.26

 vÃło

0.26

_into

0.25

Into

0.23

 INTO

0.23

 Into

0.23

Activations Density 0.134%

aspects related to the addition of new features or components in a technical context

No Comments

No Known Activations