INDEX

Explanations

references to specific medical conditions or procedures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

gun

-0.23

een

-0.23

-0.22

gen

-0.22

gie

-0.22

ë¡ľ

-0.21

gener

-0.21

à¤¼

-0.20

led

-0.20

gu

-0.20

POSITIVE LOGITS

etwork

0.30

ucle

0.27

alysis

0.23

avigator

0.23

ning

0.23

atural

0.23

ned

0.22

neau

0.21

naire

0.21

uclear

0.21

Activations Density 1.675%

references to specific medical conditions or procedures

No Comments

No Known Activations