INDEX

Explanations

grammatical structures and phrases that indicate relationships or comparisons

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

Den

-0.30

 seinen

-0.29

Den

-0.29

 keinen

-0.28

 Ihren

-0.28

 ihren

-0.27

 einen

-0.26

 unseren

-0.26

DEN

-0.25

 meinen

-0.25

POSITIVE LOGITS

der

0.47

das

0.32

die

0.31

es

0.31

der

0.31

 dieser

0.28

ein

0.25

DER

0.25

Der

0.22

die

0.22

Activations Density 0.021%

grammatical structures and phrases that indicate relationships or comparisons

No Comments

No Known Activations