INDEX

Explanations

words and phrases related to restrictions or limitations on actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ehr

-0.17

åŃĿ

-0.15

 Shields

-0.14

 caller

-0.14

eti

-0.14

enant

-0.14

åıĸæ¶Ī

-0.14

ç«ĭãģ¦

-0.13

oppins

-0.13

POSITIVE LOGITS

ouro

0.16

IID

0.16

iday

0.15

ddy

0.15

utow

0.15

ounty

0.14

uploader

0.14

ispecies

0.14

coholic

0.14

orate

0.14

Activations Density 0.001%

words and phrases related to restrictions or limitations on actions

No Comments

No Known Activations