INDEX

Explanations

specific sequences or identifiers related to social media or digital content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.24

-0.22

-0.20

uC

-0.18

ska

-0.18

-0.17

oil

-0.17

iyan

-0.17

iÃ³

-0.17

ar

-0.17

POSITIVE LOGITS

ournals

0.29

oints

0.27

0.24

eb

0.23

ourn

0.23

à¥įà¤ŀ

0.23

ÅĽcie

0.22

à¤¼

0.21

upyter

0.21

ee

0.20

Activations Density 0.106%

specific sequences or identifiers related to social media or digital content

No Comments

No Known Activations