INDEX

Explanations

references to formal announcements or statements regarding community matters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 when

-0.19

ney

-0.16

lds

-0.15

 besides

-0.14

 somebody

-0.14

 wenn

-0.14

when

-0.14

zes

-0.14

_when

-0.14

 each

-0.13

POSITIVE LOGITS

Dear

0.24

 Attached

0.23

 dear

0.23

Attached

0.23

 Dear

0.23

 attached

0.22

attached

0.20

Please

0.19

 Please

0.18

 following

0.18

Activations Density 0.191%

references to formal announcements or statements regarding community matters

No Comments

No Known Activations

references to formal announcements or statements regarding community matters

No Comments

No Known Activations