INDEX

Explanations

structured phrases indicating means or methods of achieving something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Į

-0.15

oram

-0.14

Ì§

-0.14

Ald

-0.14

ovny

-0.13

 precious

-0.13

mani

-0.13

Ã´i

-0.13

ohl

-0.13

 sing

-0.13

POSITIVE LOGITS

0.16

0.15

Nx

0.14

icie

0.14

oso

0.14

vs

0.14

áº¡p

0.14

createClass

0.14

Bot

0.13

TableModel

0.13

Activations Density 0.196%

structured phrases indicating means or methods of achieving something

No Comments

No Known Activations