INDEX

Explanations

structured data related to product attributes and details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

aret

-0.17

apy

-0.16

eparator

-0.16

rosso

-0.15

imbus

-0.15

illac

-0.15

ared

-0.14

 æ¹

-0.14

conda

-0.14

quia

-0.14

POSITIVE LOGITS

orgen

0.17

Ø²Ø±

0.16

_plural

0.14

ValueCollection

0.14

 Plantae

0.14

InternalServerError

0.14

ospace

0.14

Enum

0.14

0.13

elige

0.13

Activations Density 0.051%

structured data related to product attributes and details

No Comments

No Known Activations