INDEX

Explanations

key details about product launches and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Mour

-0.15

.synthetic

-0.15

otten

-0.15

 Sentry

-0.14

utters

-0.14

 à¤®à¤£

-0.14

 Moor

-0.14

ippers

-0.14

 liability

-0.14

uckland

-0.14

POSITIVE LOGITS

MI

0.18

opo

0.17

 vivo

0.17

 poco

0.17

opp

0.17

MIX

0.16

 selfie

0.16

 MediaTek

0.16

itel

0.16

MI

0.15

Activations Density 0.043%

key details about product launches and specifications

No Comments

No Known Activations