INDEX

Explanations

terms related to dimensions and their measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Feinstein

-0.16

ipay

-0.15

crets

-0.15

pear

-0.15

 dramatically

-0.14

odos

-0.14

 lands

-0.14

ios

-0.14

AGMA

-0.14

 modelAndView

-0.14

POSITIVE LOGITS

ality

0.17

 WithEvents

0.15

volt

0.15

PickerController

0.15

less

0.15

etting

0.15

gtest

0.15

nemonic

0.14

/color

0.14

Activations Density 0.016%

terms related to dimensions and their measurements

No Comments

No Known Activations