INDEX

Explanations

references to user interactions and navigation within a digital content context

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

Ø§ÙĨÙĩ

-0.15

abl

-0.15

ago

-0.14

are

-0.14

ajo

-0.14

ial

-0.14

azzi

-0.14

iais

-0.14

cio

-0.13

Pen

-0.13

POSITIVE LOGITS

enco

0.14

Roe

0.14

 Rupert

0.14

ilogy

0.14

achs

0.13

MLM

0.13

chein

0.13

 queryInterface

0.13

CEF

0.13

abra

0.13

Activations Density 0.005%

references to user interactions and navigation within a digital content context

No Comments

No Known Activations