INDEX

Explanations

references to distances and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 upper

-0.17

 UPPER

-0.16

ully

-0.16

umbo

-0.14

APT

-0.14

.signature

-0.14

/alert

-0.14

iddet

-0.14

upper

-0.14

(old

-0.14

POSITIVE LOGITS

-wide

0.27

-long

0.26

eters

0.23

 ÙħØ±Ø¨Ø¹

0.20

 wide

0.19

-radius

0.18

 radius

0.18

 lengths

0.18

Ã¨tres

0.18

 away

0.17

Activations Density 0.050%

references to distances and measurements

No Comments

No Known Activations