INDEX

Explanations

elements related to corrections or clarifications in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

otas

-0.14

Ä±rÄ±

-0.13

 coin

-0.13

ê

-0.13

ĥĿ

-0.13

 ëĭ´

-0.13

{}\

-0.13

 relativ

-0.13

 blunt

-0.13

iner

-0.13

POSITIVE LOGITS

 correct

0.23

 sources

0.19

æŃ£ç¡®

0.19

sources

0.19

 incorrect

0.18

incorrect

0.18

correct

0.18

_correct

0.18

 source

0.17

 Ð¸ÑģÑĤÐ¾Ñĩ

0.17

Activations Density 0.222%

elements related to corrections or clarifications in text

No Comments

No Known Activations