INDEX

Explanations

technical instructions or descriptions related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

á»©

-0.15

_rc

-0.15

 format

-0.14

enty

-0.14

 FORMAT

-0.14

Î½Ïİ

-0.14

ledon

-0.14

psy

-0.14

imity

-0.13

qus

-0.13

POSITIVE LOGITS

 different

0.23

 switch

0.22

switch

0.21

ifferent

0.21

different

0.20

 depending

0.20

 Switch

0.19

ä¸įåĲĮçļĦ

0.19

	switch

0.18

-switch

0.18

Activations Density 0.269%

technical instructions or descriptions related to products

No Comments

No Known Activations