INDEX

Explanations

key names and entities related to a specific incident or event

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

_svc

-0.17

.Tx

-0.15

à¸±à¸§à¸£

-0.15

TagName

-0.15

GH

-0.15

agher

-0.14

scoped

-0.14

gh

-0.14

gh

-0.14

agged

-0.14

POSITIVE LOGITS

 Wich

0.30

 Bangkok

0.24

orns

0.24

 Witt

0.22

 à¸ģà¸£à¸ģà¸İ

0.21

ombat

0.20

 Lump

0.20

Ph

0.20

 Watt

0.20

Pru

0.20

Activations Density 0.017%

key names and entities related to a specific incident or event

No Comments

No Known Activations