INDEX

Explanations

phrases indicating significant moments or experiences

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

steen

-0.18

ESIS

-0.18

rien

-0.17

Ø´ØªÙĩ

-0.16

esModule

-0.15

rie

-0.15

Ð¶Ð´

-0.15

ease

-0.15

ÑģÑĤÐ²

-0.14

ÑĥÐ½Ðº

-0.14

POSITIVE LOGITS

 Twist

0.15

 fart

0.15

ugo

0.15

ylon

0.15

ylan

0.14

Î»ÎµÏħ

0.14

urdy

0.14

 valign

0.14

bb

0.14

 Colleg

0.13

Activations Density 0.011%

phrases indicating significant moments or experiences

No Comments

No Known Activations