INDEX

Explanations

unique or special qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ses

-0.16

avras

-0.16

ires

-0.16

insky

-0.16

 thang

-0.15

sWith

-0.14

foundland

-0.14

iffe

-0.14

ivec

-0.14

nam

-0.14

POSITIVE LOGITS

atics

0.18

Ø¨Ø±Ø¯

0.17

rics

0.15

äºĭæĥħ

0.15

oso

0.15

bruary

0.15

ATIC

0.15

gerald

0.14

eru

0.14

Activations Density 0.000%

unique or special qualities

No Comments

No Known Activations