INDEX

Explanations

significant data points and key attributes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Tus

-0.16

ongo

-0.16

StackNavigator

-0.15

uni

-0.15

gorm

-0.15

nos

-0.14

umpt

-0.14

 Snape

-0.14

aper

-0.14

errick

-0.14

POSITIVE LOGITS

uur

0.17

ILLA

0.15

 Becker

0.14

zos

0.14

alling

0.14

 pequ

0.14

 Stat

0.14

DAC

0.14

DAM

0.13

dam

0.13

Activations Density 0.003%

significant data points and key attributes in various contexts

No Comments

No Known Activations