INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ļ¨

-0.24

ucz

-0.18

ierz

-0.18

cz

-0.17

ocz

-0.17

pis

-0.17

ariat

-0.17

atz

-0.17

acz

-0.16

zs

-0.16

POSITIVE LOGITS

ese

0.30

ise

0.28

ase

0.25

ose

0.24

iese

0.24

alse

0.23

sey

0.23

rise

0.23

sei

0.23

sea

0.23

Activations Density 0.062%

proper nouns and names

No Comments

No Known Activations