INDEX

Explanations

specific dates and numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

andin

-0.15

 Easter

-0.15

Ã©ry

-0.15

IBILITY

-0.15

linkplain

-0.15

-0.14

ercul

-0.14

 POSSIBILITY

-0.14

 ìĭ±

-0.14

Å¡ti

-0.14

POSITIVE LOGITS

EMBER

0.16

toy

0.16

çºª

0.15

ardo

0.15

wig

0.14

.setViewport

0.14

EDA

0.14

ÛĮØ±Ùĩ

0.14

embre

0.14

gim

0.14

Activations Density 0.013%

specific dates and numerical information

No Comments

No Known Activations