INDEX

Explanations

mathematical representations related to sets and functions

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

INF

-0.17

lauf

-0.17

assi

-0.16

Inf

-0.16

lest

-0.15

Interop

-0.15

lew

-0.15

lech

-0.15

 Ember

-0.14

ÙĨØ§Ø¡

-0.14

POSITIVE LOGITS

 âĪĪ

0.47

in

0.32

 thuá»Ļc

0.30

 belong

0.25

 belongs

0.24

 belonged

0.23

IN

0.23

âĪ

0.23

 belonging

0.22

-in

0.22

Activations Density 0.132%

mathematical representations related to sets and functions

No Comments

No Known Activations