INDEX

Explanations

numerical figures or data points

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

_Lean

-0.16

Ļæ±Ł

-0.15

loff

-0.14

Î¸Î®

-0.13

ecko

-0.13

ulumi

-0.13

listeners

-0.13

ToOne

-0.13

å¡ļ

-0.13

egend

-0.12

POSITIVE LOGITS

Separ

0.24

 Separ

0.23

However

0.21

 separately

0.21

Earlier

0.20

 however

0.20

 Copyright

0.19

 However

0.18

 earlier

0.18

however

0.18

Activations Density 0.049%

numerical figures or data points

No Comments

No Known Activations