INDEX

Explanations

references to trampling or violations of rights and principles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.26

ains

-0.21

-0.17

inerary

-0.17

opak

-0.17

withstanding

-0.16

htags

-0.15

POSITIVE LOGITS

ez

0.23

een

0.21

ea

0.20

eer

0.19

yt

0.18

eo

0.18

ei

0.18

aire

0.17

eur

0.17

ee

0.16

Activations Density 0.217%

references to trampling or violations of rights and principles

No Comments

No Known Activations