INDEX

Explanations

references to the name "Mel" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

elli

-0.18

ella

-0.17

esc

-0.16

Î»Î¹Î±

-0.16

link

-0.16

emi

-0.15

ëĭĿ

-0.15

otle

-0.15

edic

-0.15

lings

-0.15

POSITIVE LOGITS

ody

0.25

bourne

0.23

ting

0.23

inda

0.23

odic

0.23

atonin

0.22

anch

0.21

asma

0.21

ampus

0.20

odies

0.20

Activations Density 0.009%

references to the name "Mel" or variations thereof

No Comments

No Known Activations