INDEX

Explanations

terms related to compliance and internal processes within organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

incinn

-0.20

Ð±Ð¾ÑĤ

-0.19

ãĤ¨ãĥ«

-0.16

arken

-0.15

/Common

-0.15

íĥĿ

-0.15

noc

-0.15

enegro

-0.14

çĽŁ

-0.14

mpar

-0.14

POSITIVE LOGITS

 Controls

0.26

 controls

0.25

 escalation

0.24

 segregation

0.23

 Tone

0.23

controls

0.23

 documentary

0.21

 documented

0.21

 internal

0.21

 Documentary

0.21

Activations Density 0.022%

terms related to compliance and internal processes within organizations

No Comments

No Known Activations