INDEX

Explanations

references to historical documents or narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

%s

-0.16

assic

-0.15

 interface

-0.15

odÄĽ

-0.14

&type

-0.13

UBY

-0.13

Ø¬Ø§Øª

-0.13

Ã©nÃ©

-0.12

hoe

-0.12

 Ð·Ð°ÑģÑĤ

-0.12

POSITIVE LOGITS

fn

0.22

foot

0.22

 citation

0.22

 footnote

0.21

citation

0.21

ii

0.20

iv

0.20

FN

0.20

iii

0.20

 Foot

0.19

Activations Density 0.020%

references to historical documents or narratives

No Comments

No Known Activations