INDEX

Explanations

punctuation marks, particularly periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 ÐŀÐ´Ð½Ð°

-0.15

 ÑģÐ¾Ð¾ÑĤÐ²ÐµÑĤ

-0.15

 ÄĲÃ³

-0.15

Ãłng

-0.14

emos

-0.14

-BEGIN

-0.14

Ã¡le

-0.14

abi

-0.14

Ã¢ng

-0.14

zum

-0.13

POSITIVE LOGITS

Ide

0.17

 Inspir

0.17

 Exist

0.17

 cÃ©lib

0.17

Us

0.17

Ve

0.16

 Habit

0.16

 Moment

0.16

 Prostitutas

0.16

Pos

0.16

Activations Density 0.044%

punctuation marks, particularly periods

No Comments

No Known Activations