INDEX

Explanations

references to images or pictures in the text

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

lei

-0.19

alie

-0.17

alia

-0.15

ubern

-0.14

riet

-0.14

_rent

-0.14

ress

-0.13

Ð°ÑĢÐ°Ð½

-0.13

ConfigurationException

-0.13

room

-0.13

POSITIVE LOGITS

colo

0.29

asso

0.27

nic

0.25

.twitter

0.24

NIC

0.22

axe

0.21

cad

0.20

Pic

0.20

ilden

0.19

true

0.19

Activations Density 0.008%

references to images or pictures in the text

No Comments

No Known Activations