INDEX

Explanations

instances of violations of laws or principles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iaux

-0.17

iae

-0.17

oria

-0.17

sim

-0.14

ì¹Ń

-0.14

mie

-0.14

/he

-0.14

 folds

-0.14

ons

-0.13

ÑĢÑıÐ´Ñĥ

-0.13

POSITIVE LOGITS

isini

0.16

umont

0.15

.Popup

0.15

/problem

0.15

upert

0.15

Mey

0.15

iveness

0.14

wers

0.14

IVE

0.14

acz

0.14

Activations Density 0.025%

instances of violations of laws or principles

No Comments

No Known Activations