INDEX

Explanations

specific years mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

OrNull

-0.15

elman

-0.14

ubb

-0.14

hesive

-0.14

ÑĤÑĢÐ°

-0.14

oje

-0.14

.Meta

-0.14

ths

-0.13

aseline

-0.13

POSITIVE LOGITS

0.29

0.28

0.27

0.26

0.21

0.20

rab

0.17

st

0.17

Activations Density 0.177%

specific years mentioned in the text

No Comments

No Known Activations