INDEX

Explanations

references to the location or name "Venice."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eru

-0.15

ÑĦÐµÐºÑĤÐ¸Ð²

-0.15

 Pace

-0.15

agn

-0.15

OLS

-0.15

/avatar

-0.14

 hÃ£

-0.14

istrovstvÃŃ

-0.14

.ObjectId

-0.14

COPE

-0.14

POSITIVE LOGITS

ereal

0.23

ables

0.20

egas

0.18

itian

0.17

ues

0.17

kat

0.17

eto

0.17

ICE

0.17

ice

0.17

ison

0.17

Activations Density 0.010%

references to the location or name "Venice."

No Comments

No Known Activations