INDEX

Explanations

regulatory and compliance terms relating to disciplinary actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 courtroom

-0.16

clarations

-0.16

à¸Ńà¸Ń

-0.14

REN

-0.14

ToF

-0.13

rvÃ©

-0.13

Ð»Ð°Ñĩ

-0.13

 Courts

-0.13

.authenticate

-0.13

ibil

-0.13

POSITIVE LOGITS

 suspension

0.25

 Suspension

0.24

 disciplinary

0.23

 susp

0.22

 Ð´Ð¸ÑģÑĨÐ¸Ð¿

0.21

 suspended

0.21

 suspend

0.20

 hearing

0.20

 discipl

0.19

 Discipline

0.19

Activations Density 0.244%

regulatory and compliance terms relating to disciplinary actions

No Comments

No Known Activations