INDEX

Explanations

elements related to personal safety and security measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

aina

-0.17

èĥ½

-0.16

RIX

-0.15

erville

-0.14

olley

-0.14

ÐµÑı

-0.14

ccione

-0.13

AV

-0.13

ellen

-0.13

 parasite

-0.13

POSITIVE LOGITS

 anytime

0.28

 anywhere

0.23

 either

0.22

either

0.20

à¹Ħà¸Ķ

0.20

à¸±à¸Ļà¹Ħà¸Ķ

0.19

 à¹Ħà¸Ķ

0.18

 feas

0.18

ÑĢÐ¾ÑģÑĤÐ¾

0.18

 easily

0.17

Activations Density 0.514%

elements related to personal safety and security measures

No Comments

No Known Activations